opencode-codeops 1.8.1 → 1.10.0

package/CHANGELOG.md

@@ -2,6 +2,37 @@
 
 All notable changes to CodeOps are recorded here.
 
+## 1.10.0 — 2026-10-04
+
+### Documentation
+
+- agents: refresh managed project facts
+- routing: clarify runtime variant validation
+- plan: fix phase 3 review wording gaps
+
+### Fixes
+
+- effort: tolerate malformed message parts in marker scan
+- effort: correct phase 2 review findings
+- effort: harden helper totality and contract wording
+
+### Features
+
+- docs: add auto-effort flags and reasoning documentation
+- plan: carry reasoning suggestions through plan skills
+- effort: add session CLI and plugin runtime hooks
+- effort: add reasoning-effort contract and helper
+
+### Tests
+
+- effort: add implementation tests for reasoning-effort helper
+
+## 1.9.0 — 2026-10-04
+
+### Features
+
+- hygiene: require cleanup after every task with a temp safety net
+
 ## 1.8.1 — 2026-10-04
 
 ### Documentation

package/README.md

@@ -136,6 +136,8 @@ These standards are active without any user action. They do not need to be copie
 
 The plugin also warns (non-blocking) if any tool attempts to edit `codeops/.codeops.yml` directly — that file is managed exclusively by the `setup-codeops` skill — and if the installed skills version differs from the plugin version, so a stale install is visible.
 
+Every session also gets a workspace-hygiene guard: the plugin exports `CODEOPS_TMPDIR`, a per-session scratch directory under the OS temp directory. Skills and agents put temporary files there and delete them when the run completes; the plugin removes the directory when the session is deleted and sweeps directories abandoned by interrupted runs at session start, so CodeOps does not accumulate scratch data. The full protocol is in `_shared/workspace-hygiene.md`.
+
 ## Agent model configuration
 
 All CodeOps subagents inherit the model of the primary agent that invoked them. No provider-specific configuration is required out of the box.
@@ -151,6 +153,22 @@ To pin specific models per role, use the `setup-routing` skill or add overrides
 }
 ```
 
+### Adaptive reasoning effort
+
+CodeOps can pick a reasoning level per dispatch instead of always inheriting the parent session's
+variant. A dispatch packet may carry one standalone marker line:
+
+```text
+[codeops-effort: medium]
+```
+
+Reasoning-heavy skills also accept `--auto-effort` (use the skill's recommended level) or
+`--auto-effort=high` (explicit level), announce it, and clear it before the final run summary.
+Resolution order: dispatch marker, then session `--auto-effort`, then
+`routing.roles.<agent>.reasoning` in `codeops/codeops.json`, then the inherited parent variant.
+The levels are suggestions: no permission, verification step, or review gate ever reads them. The
+full contract is in `_shared/reasoning-effort.md`.
+
 ## Project specialists
 
 CodeOps can recommend project-specific specialist subagents when repository evidence shows a

package/_shared/quality-profile.md

@@ -107,6 +107,11 @@ or response content.
 | design-challenger | Problem + candidate options, **without** the parent's preferred choice (per `_shared/recommendation-hardening.md`) |
 | codebase-scout | The factual questions, search hints, and the facts-only contract |
 
+Every packet also carries the session temp root (`$CODEOPS_TMPDIR`) and the hygiene requirement:
+the agent creates temporary files only under that root and deletes its own before returning (see
+`_shared/workspace-hygiene.md`). A parent never deletes a subagent's artifacts while its dispatch
+is still in flight.
+
 ## Project specialists
 
 A project may define specialist roles on top of the catalog (see `_shared/specialist-agents.md`).
@@ -142,6 +147,10 @@ Resolution order is:
 3. project `[agents]` defaults in `opencode.json`;
 4. the parent session's model and effort.
 
+For the runtime reasoning-effort override (a dispatch marker, a session `--auto-effort` level, or
+a routing role default), see [reasoning-effort.md](reasoning-effort.md); the static resolution
+order above is unchanged.
+
 Use `python3 "${CODEOPS_PLUGIN_ROOT}/scripts/install_agents.py" --project . --roles ...` to create optional project agents. Generated agent files carry a CodeOps marker. The installer owns only marked files and preserves every hand-authored file. Use `--check` to detect missing or stale generated agents and `--dry-run` to preview changes. Project specialists are generated with `--custom <role>` from `codeops/specialists/<role>.md` and indexed into `AGENTS.md` with `--sync-agents-md`; their routing policy may also set `reasoning`.
 
 Dynamic packets are the correctness baseline. If a named agent is missing or a model pin is unavailable, spawn a generic subagent with the complete packet or run inline. Report the fallback and preserve required reviewer independence, sandbox intent, and every ambiguity/readiness/verification gate.

package/_shared/reasoning-effort.md

@@ -0,0 +1,135 @@
+# Reasoning effort (shared contract)
+
+> **CodeOps Artifact Schema**: 1
+
+CodeOps subagents normally inherit the parent session's model variant, so a top-tier parent
+would pay top-tier reasoning cost for every child dispatch. Adaptive reasoning effort lets an
+explicit source pick a level per dispatch or per skill run. This document is the shipped
+contract consumed by the plugin and the skills. It is advisory by design and never a gate.
+
+## Levels
+
+| Level | Meaning | Typical work |
+| ----- | ------- | ------------ |
+| `low` | Mechanical, fully specified, deterministic verification | Docs and formatting edits, renames, config updates |
+| `medium` | Ordinary bounded feature work with known patterns | Standard implementation phases, recon, single-file reviews |
+| `high` | Correctness- or security-sensitive, cross-cutting, or planning/review work | Requirements, planning, correctness/security review, ambiguous implementation |
+| `max` | Adversarial or high-risk analysis where a missed detail is costly | Thorough preflight, complex or sensitive phases |
+
+The four levels are the complete suggestion vocabulary. A level is applied only when the
+runtime model exposes a matching variant, or when the model reports reasoning support but has no
+variant record (the level is then written directly as the provider reasoning option). A level
+the model does not expose leaves the request unchanged and never raises a provider error.
+Routing policy is project configuration, not a suggestion:
+`routing.roles.<agent>.reasoning` may name any value from the provider enum
+(`none`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max`).
+
+## Marker grammar
+
+A dispatch marker is one standalone line in a dispatch message:
+
+```text
+[codeops-effort: <level>]
+```
+
+- The whole trimmed line must match `^\[codeops-effort:\s*(low|medium|high|max)\]\s*$`.
+- The level is exactly lower-case. Unknown or malformed markers are ignored, never errors.
+- Only user-role text parts of a message are scanned; tool output, diffs, and quoted documents
+  are never scanned.
+- The first valid marker in message order wins; additional markers are ignored.
+- The marker is deliberately distinct from the human-readable plan line
+  `> **Reasoning**: ...`, so a quoted plan line can never act as a machine directive.
+
+For quality-agent packets the marker follows the dispatch header; for packet kinds without a
+header it is the first line. `exec-plan` owns the composition rule.
+
+## Precedence
+
+The most specific source wins:
+
+```text
+dispatch marker  >  session auto-effort  >  routing.roles[<agent>].reasoning  >  inherit parent variant
+```
+
+| Source | Scope | Owner |
+| ------ | ----- | ----- |
+| Dispatch marker | One child dispatch | `exec-plan` composes it from the phase suggestion or the run's forced level |
+| Session auto-effort | One skill run in the user's session | `--auto-effort` through `scripts/codeops_effort.py` |
+| Routing role default | Project policy for one agent name | `codeops/codeops.json` → `routing.roles.<agent>.reasoning` |
+| Inherit | Everything else | The child keeps the parent model and variant |
+
+Routing lookup applies only when the dispatching agent's name has an explicit `routing.roles`
+entry. There are no built-in catalog defaults, hand-authored agents are untouched, and
+generated specialists keep their embedded value unless the project adds a routing entry.
+
+## Skill recommendation table
+
+Used for suggestions and for a bare `--auto-effort`:
+
+| Skill | Recommended level | Notes |
+| ----- | ----------------- | ----- |
+| `make-requirements` | `high` | Structured discovery and gap expansion |
+| `make-plan` | `high` | Decomposition plus the Zero-Ambiguity Gate |
+| `preflight` | `high`; `max` with `--thorough` | Adversarial multi-dimension audit |
+| `grill-me` | `high` | Branch-by-branch disambiguation |
+| `exec-plan` | current phase's `Reasoning:` level | Bare flag follows the phase; `=<level>` forces a constant |
+| `retro-requirements` | `high` | Nine-phase archaeology |
+| `upgrade-plan` | `high` | Content gate plus structural migration |
+| `setup-codeops`, `setup-routing` | `high` (reference only) | Structure and policy authoring |
+| `techdocs`, `analyze-project`, `clean-comments`, `outcome-review` | `medium` (reference only) | Structured but bounded |
+| `roadmap`, `git-commit`, `github-issues` | `low` (reference only) | Mechanical bookkeeping |
+
+Skills that accept `--auto-effort` are `make-requirements`, `make-plan`, `preflight`,
+`grill-me`, `exec-plan`, `retro-requirements`, and `upgrade-plan`. Other skills document their
+recommended levels for reference only and do not implement the flag.
+
+## Plan suggestion derivation
+
+`make-plan` derives an advisory level for every phase and every task mini-plan from signals it
+already records:
+
+| Signal | Suggested level |
+| ------ | --------------- |
+| Phase carries a complexity escalation approval, or a complex/sensitive tag | `max` |
+| Phase carries a security, financial-integrity, concurrency, performance-critical, compiler-semantics, or migration lens/risk tag | `high` |
+| Docs/config/rename-only phase with deterministic verification | `low` |
+| Any other non-trivial phase | `medium` |
+
+The line is written as `> **Reasoning**: <level> — <one-line reason>`. It is a suggestion: the
+user may edit or delete it, and `exec-plan` never blocks on it. A plan without the line keeps
+the inherited behavior.
+
+## Auto-effort option
+
+Skills listed above accept the flag. Parsing follows the existing standalone-token pattern
+(`--auto-design`, `--explore-scope`): exactly one occurrence before the first `--` sentinel,
+removed before resolving targets, paths, or modes; zero means advise-only; more than one or an
+invalid `=<level>` is an argument error.
+
+| Flag | Behavior |
+| ---- | -------- |
+| *(absent)* | Print `Suggested reasoning: <level> — <reason>` once at start (`exec-plan`: before each phase); change nothing |
+| `--auto-effort` | Use the skill's recommended level (`exec-plan`: the current phase level) |
+| `--auto-effort=<level>` | Use the named level; reject values outside the four-level set |
+
+Semantics:
+
+1. Announce `Auto-effort active — reasoning <level> applied for this run`.
+2. Record the level for the session run through `scripts/codeops_effort.py`.
+3. Clear it at run completion, before the final summary.
+4. Run-scoped: the level applies from the point it is set until cleared or the session ends.
+5. Fail-open: when the session temp directory is unavailable or the helper fails, print an
+   advise-only note and continue; the skill never blocks.
+6. Never a gate: effort affects cost and latency only. No readiness check, verification step,
+   reviewer requirement, or finding gate may read it.
+
+For `exec-plan`, a bare flag follows each phase's suggestion, while `--auto-effort=<level>`
+forces that level for the whole run, including every dispatch marker composed during it.
+
+## Suggestion-only guarantee
+
+| Allowed | Forbidden |
+| ------- | --------- |
+| Printing a suggested level and its reason | Blocking a run because a level is missing or unsupported |
+| Applying a level when a marker, flag, or routing entry explicitly asks | Overriding an explicit user plan edit with a derived default |
+| Reporting the applied level and its source | Treating effort as an acceptance, review, or security control |

package/_shared/workspace-hygiene.md

@@ -0,0 +1,53 @@
+# Workspace hygiene (shared convention)
+
+> **CodeOps Artifact Schema**: 1
+
+This is the **single canonical definition** of CodeOps temporary-artifact hygiene. Every skill,
+agent, and script that creates files outside its assigned deliverables follows it. Skills link
+here instead of carrying copies.
+
+## Temporary artifacts
+
+A temporary artifact is any file or directory a run creates that is not a durable deliverable:
+verification logs, diffs, patch files, commit-message files, scratch directories, fixture trees,
+downloaded artifacts, and intermediate reports. Code, tests, plan documents, and other assigned
+outputs are deliverables — not temporary artifacts — and they are never deleted here.
+
+## Where temporary artifacts live
+
+1. `$CODEOPS_TMPDIR` when the CodeOps plugin exports it (one directory per session). Use it for
+   every scratch file.
+2. Otherwise, the operating system's temp directory.
+3. Never inside the repository. A repository path is durable space; scratch does not belong there.
+
+Create subdirectories under the temp root lazily, only when the task needs them.
+
+## Lifecycle
+
+1. **Create lazily** — write a temporary file only when the task needs it.
+2. **Keep only while needed** — one artifact per purpose; no accumulating copies.
+3. **Delete before reporting completion** — every task, phase, skill run, and session ends with a
+   cleanup pass that removes the files and directories the run created, including verification
+   logs.
+4. **Report the result** — the final summary states `Cleanup: done`, or names the artifact that
+   was kept and why. If a deletion fails, report the path and the reason.
+
+## Safe deletion rules (non-negotiable)
+
+- Delete only files you created, and only under the sanctioned temp root.
+- Never delete user files, repository content, versioned artifacts, `codeops/` planning artifacts,
+  or git worktrees.
+- Never delete another session's temporary files.
+- Never follow a symlink out of the temp root; treat a symlinked entry as foreign and leave it.
+- Never run a broad recursive delete against a path that may be empty or unset; resolve and verify
+  the path first.
+- A temporary file must not hold secrets. If one does, delete it and say so without printing its
+  contents.
+- If the user asks for an artifact to be kept, name its exact path and keep that file only.
+
+## Automatic safety net
+
+The CodeOps plugin exports `$CODEOPS_TMPDIR` for each session and removes that session's directory
+when the session is deleted. At session start it also removes CodeOps temp directories older than
+seven days, so an interrupted run cannot leak storage forever. The safety net is a fallback, not a
+substitute: the run itself still performs the cleanup pass above.

package/agent-templates/codebase-scout.md

@@ -15,3 +15,9 @@ questions, optional search hints, and the facts-only contract from `_shared/qual
   answer. No summaries of things nobody asked about.
 - If a question is too ambiguous to search for, report that ambiguity as the answer to that
   question — never substitute your own interpretation.
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — logs, diffs, patches,
+  scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS temp
+  directory), never inside the repository. Delete everything you created before reporting done.
+  Never delete user files, versioned artifacts, worktrees, or another session's temporary files.
+  If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agent-templates/concurrency-auditor.md

@@ -3,3 +3,10 @@
      Do not add YAML frontmatter here — use install_agents.py to generate agent files. -->
 
 Audit exactly the supplied change packet. Establish shared state, ownership, synchronization, ordering, cancellation, retry, timeout, and failure semantics before judging the diff. Hunt for data races, check-then-act gaps, lost updates, deadlocks, starvation, unsafe publication, reentrancy, duplicate work, stale reads, partial commits, and unbounded concurrency. Construct realistic interleavings that could violate stated invariants. Cite file and line evidence and distinguish proven defects from unverified risk. Return surviving findings with severity, interleaving, violated invariant, and remedy, or an explicit clean result. Remain read-only.
+
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — logs, diffs, patches,
+  scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS temp
+  directory), never inside the repository. Delete everything you created before reporting done.
+  Never delete user files, versioned artifacts, worktrees, or another session's temporary files.
+  If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agent-templates/design-challenger.md

@@ -24,3 +24,9 @@ caps live in `_shared/recommendation-hardening.md`; the packet convention lives
   disagreement is precisely the value you add.
 - If the problem statement is too thin to challenge — missing constraints, options that are not
   actually distinct, no success criterion — report that as your finding instead of guessing.
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — logs, diffs, patches,
+  scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS temp
+  directory), never inside the repository. Delete everything you created before reporting done.
+  Never delete user files, versioned artifacts, worktrees, or another session's temporary files.
+  If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agent-templates/domain-specialist-executor.md

@@ -18,3 +18,9 @@ one dispatched unit — normally a whole phase, occasionally a single task — w
 - Never copy plan, requirement, ambiguity-register, or test-case identifiers, or `codeops/`,
   `plans/`, or `requirements/` paths, into code or doc comments. Those files are ephemeral; keep
   the behavior and drop the citation.
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — verify logs, diffs,
+  patches, scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS
+  temp directory), never inside the repository. Delete everything you created before reporting
+  done. Never delete user files, versioned artifacts, worktrees, or another session's temporary
+  files. If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agent-templates/domain-specialist-reviewer.md

@@ -15,3 +15,9 @@ to a dispatched phase diff as an additional, independent reviewer.
   implemented.
 - Keep the output terse and structured so the parent can merge it directly: findings first, then
   explicit open questions, then "no findings" if applicable. Do not restate the diff.
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — logs, diffs, patches,
+  scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS temp
+  directory), never inside the repository. Delete everything you created before reporting done.
+  Never delete user files, versioned artifacts, worktrees, or another session's temporary files.
+  If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agent-templates/financial-integrity-auditor.md

@@ -3,3 +3,10 @@
      Do not add YAML frontmatter here — use install_agents.py to generate agent files. -->
 
 Audit exactly the supplied change packet. Treat monetary correctness and auditability as invariants. Check balanced accounting, integer minor-unit or explicitly justified decimal arithmetic, currency/unit consistency, idempotency and duplicate submission, transaction atomicity, retry and partial-failure behavior, reconciliation, authorization, immutable audit evidence, overflow and negative amounts, time boundaries, and reversal/refund semantics. Attempt to falsify every claimed invariant using concrete counterexamples. Cite file and line evidence. Return only surviving findings with severity, violated invariant, failure scenario, and remedy, or an explicit clean result. Remain read-only and do not accept implementation convenience as a reason to weaken financial semantics.
+
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — logs, diffs, patches,
+  scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS temp
+  directory), never inside the repository. Delete everything you created before reporting done.
+  Never delete user files, versioned artifacts, worktrees, or another session's temporary files.
+  If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agent-templates/perf-auditor.md

@@ -21,3 +21,9 @@ its last result). The conventions behind the packet live in `_shared/quality-pro
   (searching call sites, counting occurrences); never for mutation.
 - If the packet is insufficient — no diff, no sense of which paths are hot — STOP and report
   exactly what is missing as a blocker. Never guess.
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — logs, diffs, patches,
+  scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS temp
+  directory), never inside the repository. Delete everything you created before reporting done.
+  Never delete user files, versioned artifacts, worktrees, or another session's temporary files.
+  If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agent-templates/phase-reviewer.md

@@ -52,3 +52,9 @@ The conventions behind the packet live in
 - If the packet is insufficient — no diff, contradictory lens set, missing verify context — STOP
   and report exactly what is missing as a blocker. Never guess and never review substitute
   content you found on your own.
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — logs, diffs, patches,
+  scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS temp
+  directory), never inside the repository. Delete everything you created before reporting done.
+  Never delete user files, versioned artifacts, worktrees, or another session's temporary files.
+  If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agent-templates/plan-task-executor-opus.md

@@ -44,3 +44,9 @@ parent.
   exactly what is missing or ambiguous as a blocker — never guess, and never edit the
   execution plan or roadmap (the parent session owns those and the user conversation).
 - Report per task: what changed, test status, and residual risk.
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — verify logs, diffs,
+  patches, scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS
+  temp directory), never inside the repository. Delete everything you created before reporting
+  done. Never delete user files, versioned artifacts, worktrees, or another session's temporary
+  files. If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agent-templates/plan-task-executor.md

@@ -41,3 +41,9 @@ original-goal or smallest-design context blocks execution; report it to the pare
   exactly what is missing or ambiguous as a blocker — never guess, and never edit the
   execution plan or roadmap (the parent session owns those and the user conversation).
 - Report per task, 3-4 lines each: what changed, test status, any blocker.
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — verify logs, diffs,
+  patches, scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS
+  temp directory), never inside the repository. Delete everything you created before reporting
+  done. Never delete user files, versioned artifacts, worktrees, or another session's temporary
+  files. If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agent-templates/preflight-auditor.md

@@ -43,3 +43,9 @@ in the preflight skill.
 - **Read-only.** You never edit the artifact or the code. Bash is for inspection only.
 - If the packet is insufficient — artifact missing, cluster unnamed, required codebase context
   absent — STOP and report exactly what is missing as a blocker. Never guess.
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — logs, diffs, patches,
+  scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS temp
+  directory), never inside the repository. Delete everything you created before reporting done.
+  Never delete user files, versioned artifacts, worktrees, or another session's temporary files.
+  If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agent-templates/security-auditor.md

@@ -40,3 +40,9 @@ active checklist below — never one dispatch per profile. The profile names are
 - **Read-only.** You never edit files, apply fixes, or commit. Bash is for inspection only.
 - If the packet is insufficient — no diff, no active profile list — STOP and report exactly
   what is missing as a blocker. Never guess.
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — logs, diffs, patches,
+  scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS temp
+  directory), never inside the repository. Delete everything you created before reporting done.
+  Never delete user files, versioned artifacts, worktrees, or another session's temporary files.
+  If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agent-templates/semantics-reviewer.md

@@ -3,3 +3,10 @@
      Do not add YAML frontmatter here — use install_agents.py to generate agent files. -->
 
 Review exactly the supplied semantic specification or implementation packet. Trace behavior across syntax/decoding, name or identity resolution, typing/validation, intermediate representations, evaluation/lowering, optimization/transformation, diagnostics, serialization, and compatibility as applicable. Seek ambiguous rules, non-total behavior, phase disagreement, unsound transformations, nondeterminism, invalid recovery, and diagnostics that expose implementation accidents. Use counterexamples and minimal programs/messages to falsify the claimed semantics. Cite evidence and return surviving findings with severity, example, affected phases, and resolution, or an explicit clean result. Remain read-only.
+
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — logs, diffs, patches,
+  scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS temp
+  directory), never inside the repository. Delete everything you created before reporting done.
+  Never delete user files, versioned artifacts, worktrees, or another session's temporary files.
+  If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agent-templates/spec-test-author.md

@@ -27,3 +27,9 @@ command). The conventions behind the packet live in `_shared/quality-profile.md`
 - If the packet is insufficient — an interface signature missing, a case ambiguous, framework
   conventions unclear — STOP and report exactly what is missing as a blocker. Never guess an
   expectation and never peek at the implementation to resolve doubt.
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — logs, diffs, patches,
+  scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS temp
+  directory), never inside the repository. Delete everything you created before reporting done.
+  Never delete user files, versioned artifacts, worktrees, or another session's temporary files.
+  If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agents/concurrency-auditor.md

@@ -13,3 +13,10 @@ permission:
 ---
 
 Audit exactly the supplied change packet. Establish shared state, ownership, synchronization, ordering, cancellation, retry, timeout, and failure semantics before judging the diff. Hunt for data races, check-then-act gaps, lost updates, deadlocks, starvation, unsafe publication, reentrancy, duplicate work, stale reads, partial commits, and unbounded concurrency. Construct realistic interleavings that could violate stated invariants. Cite file and line evidence and distinguish proven defects from unverified risk. Return surviving findings with severity, interleaving, violated invariant, and remedy, or an explicit clean result. Remain read-only.
+
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — logs, diffs, patches,
+  scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS temp
+  directory), never inside the repository. Delete everything you created before reporting done.
+  Never delete user files, versioned artifacts, worktrees, or another session's temporary files.
+  If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agents/correctness-reviewer.md

@@ -64,3 +64,9 @@ The conventions behind the packet live in
 - If the packet is insufficient — no diff, contradictory lens set, missing verify context — STOP
   and report exactly what is missing as a blocker. Never guess and never review substitute
   content you found on your own.
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — logs, diffs, patches,
+  scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS temp
+  directory), never inside the repository. Delete everything you created before reporting done.
+  Never delete user files, versioned artifacts, worktrees, or another session's temporary files.
+  If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agents/demanding-executor.md

@@ -56,3 +56,9 @@ parent.
   exactly what is missing or ambiguous as a blocker — never guess, and never edit the
   execution plan or roadmap (the parent session owns those and the user conversation).
 - Report per task: what changed, test status, and residual risk.
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — verify logs, diffs,
+  patches, scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS
+  temp directory), never inside the repository. Delete everything you created before reporting
+  done. Never delete user files, versioned artifacts, worktrees, or another session's temporary
+  files. If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agents/design-challenger.md

@@ -36,3 +36,9 @@ caps live in `_shared/recommendation-hardening.md`; the packet convention lives
   disagreement is precisely the value you add.
 - If the problem statement is too thin to challenge — missing constraints, options that are not
   actually distinct, no success criterion — report that as your finding instead of guessing.
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — logs, diffs, patches,
+  scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS temp
+  directory), never inside the repository. Delete everything you created before reporting done.
+  Never delete user files, versioned artifacts, worktrees, or another session's temporary files.
+  If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agents/executor.md

@@ -53,3 +53,9 @@ original-goal or smallest-design context blocks execution; report it to the pare
   exactly what is missing or ambiguous as a blocker — never guess, and never edit the
   execution plan or roadmap (the parent session owns those and the user conversation).
 - Report per task, 3-4 lines each: what changed, test status, any blocker.
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — verify logs, diffs,
+  patches, scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS
+  temp directory), never inside the repository. Delete everything you created before reporting
+  done. Never delete user files, versioned artifacts, worktrees, or another session's temporary
+  files. If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agents/explorer.md

@@ -27,3 +27,9 @@ questions, optional search hints, and the facts-only contract from `_shared/qual
   answer. No summaries of things nobody asked about.
 - If a question is too ambiguous to search for, report that ambiguity as the answer to that
   question — never substitute your own interpretation.
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — logs, diffs, patches,
+  scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS temp
+  directory), never inside the repository. Delete everything you created before reporting done.
+  Never delete user files, versioned artifacts, worktrees, or another session's temporary files.
+  If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agents/financial-integrity-auditor.md

@@ -13,3 +13,10 @@ permission:
 ---
 
 Audit exactly the supplied change packet. Treat monetary correctness and auditability as invariants. Check balanced accounting, integer minor-unit or explicitly justified decimal arithmetic, currency/unit consistency, idempotency and duplicate submission, transaction atomicity, retry and partial-failure behavior, reconciliation, authorization, immutable audit evidence, overflow and negative amounts, time boundaries, and reversal/refund semantics. Attempt to falsify every claimed invariant using concrete counterexamples. Cite file and line evidence. Return only surviving findings with severity, violated invariant, failure scenario, and remedy, or an explicit clean result. Remain read-only and do not accept implementation convenience as a reason to weaken financial semantics.
+
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — logs, diffs, patches,
+  scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS temp
+  directory), never inside the repository. Delete everything you created before reporting done.
+  Never delete user files, versioned artifacts, worktrees, or another session's temporary files.
+  If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agents/performance-auditor.md

@@ -33,3 +33,9 @@ its last result). The conventions behind the packet live in `_shared/quality-pro
   (searching call sites, counting occurrences); never for mutation.
 - If the packet is insufficient — no diff, no sense of which paths are hot — STOP and report
   exactly what is missing as a blocker. Never guess.
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — logs, diffs, patches,
+  scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS temp
+  directory), never inside the repository. Delete everything you created before reporting done.
+  Never delete user files, versioned artifacts, worktrees, or another session's temporary files.
+  If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agents/preflight-auditor.md

@@ -55,3 +55,9 @@ in the preflight skill.
 - **Read-only.** You never edit the artifact or the code. Bash is for inspection only.
 - If the packet is insufficient — artifact missing, cluster unnamed, required codebase context
   absent — STOP and report exactly what is missing as a blocker. Never guess.
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — logs, diffs, patches,
+  scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS temp
+  directory), never inside the repository. Delete everything you created before reporting done.
+  Never delete user files, versioned artifacts, worktrees, or another session's temporary files.
+  If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agents/security-auditor.md

@@ -52,3 +52,9 @@ active checklist below — never one dispatch per profile. The profile names are
 - **Read-only.** You never edit files, apply fixes, or commit. Bash is for inspection only.
 - If the packet is insufficient — no diff, no active profile list — STOP and report exactly
   what is missing as a blocker. Never guess.
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — logs, diffs, patches,
+  scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS temp
+  directory), never inside the repository. Delete everything you created before reporting done.
+  Never delete user files, versioned artifacts, worktrees, or another session's temporary files.
+  If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agents/semantics-reviewer.md

@@ -13,3 +13,10 @@ permission:
 ---
 
 Review exactly the supplied semantic specification or implementation packet. Trace behavior across syntax/decoding, name or identity resolution, typing/validation, intermediate representations, evaluation/lowering, optimization/transformation, diagnostics, serialization, and compatibility as applicable. Seek ambiguous rules, non-total behavior, phase disagreement, unsound transformations, nondeterminism, invalid recovery, and diagnostics that expose implementation accidents. Use counterexamples and minimal programs/messages to falsify the claimed semantics. Cite evidence and return surviving findings with severity, example, affected phases, and resolution, or an explicit clean result. Remain read-only.
+
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — logs, diffs, patches,
+  scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS temp
+  directory), never inside the repository. Delete everything you created before reporting done.
+  Never delete user files, versioned artifacts, worktrees, or another session's temporary files.
+  If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.

package/agents/spec-test-author.md

@@ -39,3 +39,9 @@ command). The conventions behind the packet live in `_shared/quality-profile.md`
 - If the packet is insufficient — an interface signature missing, a case ambiguous, framework
   conventions unclear — STOP and report exactly what is missing as a blocker. Never guess an
   expectation and never peek at the implementation to resolve doubt.
+- **Workspace hygiene (non-negotiable).** Temporary artifacts you create — logs, diffs, patches,
+  scratch directories — belong under `$CODEOPS_TMPDIR` when it is set (otherwise the OS temp
+  directory), never inside the repository. Delete everything you created before reporting done.
+  Never delete user files, versioned artifacts, worktrees, or another session's temporary files.
+  If an artifact must outlive the task, name it and say why. Full rules:
+  `_shared/workspace-hygiene.md`.