@event4u/agent-config 5.10.0 → 6.0.0

package/.agent-src/skills/command-writing/SKILL.md

@@ -1,282 +0,0 @@
----
-model_tier: inherit
-name: command-writing
-description: "Use when creating or editing a slash command in .agent-src.uncondensed/commands/ — frontmatter, numbered steps, safety gates — even when the user just says 'add a /command for X'."
-domain: process
-workspaces:
-  - agent-config-maintainer
-packs:
-  - meta
----
-
-<!-- cloud_safe: degrade -->
-
-# command-writing
-
-## When to use
-
-* Creating a new slash command in `.agent-src.uncondensed/commands/{name}.md`
-* Rewriting an existing command (not a typo fix)
-* Deciding whether a request should be a command at all
-* Splitting an oversized command into smaller ones
-
-Do NOT use this skill when:
-
-* The content is a constraint the agent must always honor → use `rule-writing`
-* The content is reference knowledge agents cite → use `guideline-writing`
-* The content is a triggered workflow invoked by the model → use `skill-writing`
-
-## Command vs skill — critical test
-
-| Intent | Artifact |
-|---|---|
-| "User types `/foo` to explicitly run this" | **Command** |
-| "Agent picks this up from description match" | **Skill** |
-
-A command is **user-invoked** and carries `disable-model-invocation: true`.
-A skill is model-invoked via description routing. If both audiences apply,
-author as a skill and add a thin command that delegates to it.
-
-## Commands ARE Claude skills (projection reality)
-
-Every `.agent-src.uncondensed/commands/{name}.md` projects to
-`.claude/skills/{slug}/SKILL.md` via `scripts/condense.py`
-(`generate_claude_commands`). Nested commands flatten with `-`
-(`council/default.md` → `council-default`). Skills + commands share the
-**same `.claude/skills/` namespace** — Claude does not distinguish them.
-
-Authoring consequences:
-
-* Frontmatter `description` is Claude's **routing surface**. Generic
-  phrasing → undertriggering even with `disable-model-invocation: true`,
-  because the in-host suggester, fuzzy search, and any tooling that
-  scans `.claude/skills/` ranks by description match.
-* `disable-model-invocation: true` blocks **automatic** invocation only.
-  It does NOT remove the command from discovery surfaces. Weak
-  description = invisible to the suggester even when intent matches.
-* Trigger phrasing follows the same Iron Law as skill descriptions:
-  name 2+ trigger classes (domains, symptoms, user phrasing), end with
-  the `... even when the user just says ...` tail, ≤ 200 chars. See
-  `skill-writing` § 1b for the canonical before/after.
-* `suggestion.trigger_description` / `suggestion.trigger_context` are
-  **separate** from frontmatter `description` — they drive the in-host
-  suggester (`command-suggestion-policy`), not Claude's skill router.
-  Both matter, both must be precise.
-
-Bottom line: write the command's `description` as if a skill router
-will read it — because one will.
-
-## Procedure
-
-### 0. Run the Drafting Protocol
-
-Creating or materially rewriting a command **must** go through Understand →
-Research → Draft from the
-[`artifact-drafting-protocol`](../../rules/artifact-drafting-protocol.md) rule.
-
-* **Understand** — what user-facing problem does `/{name}` solve in one
-  session? What are the inputs, outputs, side effects?
-* **Research** — **inspect** `.agent-src.uncondensed/templates/command.md`,
-  grep `commands/` for overlap, and **analyze** 1–2 peer commands
-  (e.g. `create-pr`, `commit`).
-* **Draft** — propose frontmatter (`name`, `description`) first, then the
-  step skeleton. Only fill bodies after both are confirmed.
-
-### 1. Use the template
-
-Canonical source: `.agent-src.uncondensed/templates/command.md`.
-
-Minimum frontmatter:
-
-```yaml
----
-name: {command-name}          # must match filename without .md
-description: "Short human-readable summary of what /{name} does"
-disable-model-invocation: true
-skills: [optional-skill-1]    # optional — skills this command delegates to
-suggestion:                   # required (road-to-context-aware-command-suggestion Phase 2)
-  eligible: true              # default; set false to opt out of auto-surfacing
-  trigger_description: "natural-language pattern, comma-separated examples"
-  trigger_context: "concrete signal — branch name, file pattern, recent tool output"
----
-```
-
-Or, when opting out:
-
-```yaml
-suggestion:
-  eligible: false
-  rationale: "one-line reason this command must be invoked deliberately"
-```
-
-Suggestion-block rules (linter-enforced):
-
-* `eligible` is **required** and must be `true` or `false`.
-* `eligible: true` → both `trigger_description` and `trigger_context` must be
-  non-empty (≥ 10 chars each); the linter rejects empty or overly generic
-  patterns. The suggestion layer never auto-executes; the user always picks.
-* `eligible: false` → `rationale` must be non-empty. Use the opt-out for
-  intentional-only invocations (settings mutations, destructive actions,
-  package-internal tools, niche maintenance).
-* Optional `confidence_floor` (0.0–1.0) and `cooldown` (e.g. `10m`)
-  override the global settings per command.
-
-Eligibility decisions are tracked in
-[`agents/settings/contexts/command-suggestion-eligibility.md`](../../../agents/settings/contexts/command-suggestion-eligibility.md).
-Add or revise entries there before changing a command's `suggestion` block.
-
-When iterating on the description, delegate to the
-[`description-assist`](../description-assist/SKILL.md) skill — approval-gated,
-no silent edits, max two rounds.
-
-### 2. Structure the body
-
-Required sections in this order:
-
-1. `# /{name}` heading + one-line summary
-2. **Source of truth note** — works on `.agent-src.uncondensed/`, never on
-   generated directories
-3. `## Steps` — numbered sub-headings `### 1.`, `### 2.`, ...
-4. Final step **presents findings** and asks the user before destructive
-   changes (numbered options per `user-interaction` rule)
-5. Optional `## Rules` — short, command-specific constraints
-
-### 3. Enforce safety gates
-
-* No auto-apply of destructive actions without user confirmation.
-* Every step with side effects (git push, file delete, PR merge) asks first.
-* If the command calls external APIs, list required keys / permissions.
-* If the command edits agent files, target `.agent-src.uncondensed/` only.
-
-### 3b. Path conventions in command body
-
-Body links to guidelines / contracts use the verbatim relative form
-(`../../docs/guidelines/...`, `../../docs/contracts/...`); the
-condense-time rewriter handles depth. Do not pre-rewrite in source. Do
-not write `.agent-src.uncondensed/` in any markdown link target — the
-file ships into `.augment/commands/` and the prefix breaks consumer
-resolution. The only legitimate `.agent-src.uncondensed/` strings in a
-command file are prose mentions and step instructions about where to
-edit (per § 2 above). Canonical reference: `rule-writing` § 3b.
-
-### 4. Enforce the size budget
-
-Normative source: [`size-enforcement`](../../rules/size-enforcement.md) +
-`docs/guidelines/agent-infra/size-and-scope.md`.
-
-| Category | Target |
-|---|---|
-| Ideal | ≤ 120 lines |
-| Acceptable | ≤ 200 lines |
-| Split signal | > 250 lines |
-
-Commands orchestrate, they do not implement detail. If a step needs a
-multi-paragraph explanation, extract it into a skill and call it.
-
-### 5. Validate
-
-* Run `python3 scripts/skill_linter.py .agent-src.uncondensed/commands/{name}.md`
-  → 0 FAIL.
-* Run `bash scripts/condense.sh --sync` → regenerates `.agent-src/commands/{name}.md`.
-* Run `python3 scripts/condense.py --generate-tools` → creates the Claude symlink at
-  `.claude/skills/{name}/SKILL.md`.
-* Run the full CI pipeline locally (see `Taskfile.yml` in this repo for
-  the script list) — must exit 0 except for tolerated warnings.
-
-### 6. Governance baseline (when introducing a new linter check)
-
-**Advisory, reviewer-checked — no CI gate.** When the same PR adds a
-new check to `scripts/skill_linter.py` (or strengthens an existing one)
-such that previously-clean commands now warn, the PR body MUST record
-the pre-existing violations on `main` in a Markdown table:
-
-```markdown
-### Pre-existing baseline (informational)
-
-| Code | Count on main | Bucket |
-|---|---:|---|
-| {new_code} | N | (a) genuine fix · (b) accept · (c) check too aggressive |
-```
-
-Forward-only: the new check applies to **the file under review** and to
-**future** edits. The baseline table is informational so reviewers can
-spot intent (fix-now vs. backlog) without diffing the full lint output.
-See `agents/evidence/analysis/lint-warning-triage.md` for the 3-bucket reference.
-
-## Output format
-
-1. Complete command file at `.agent-src.uncondensed/commands/{name}.md`
-2. Frontmatter populated, `disable-model-invocation: true` present
-3. Linter output showing 0 FAIL
-4. Generated Claude symlink verified
-
-## Gotchas
-
-* Forgetting `disable-model-invocation: true` — the model will auto-invoke
-  the command as if it were a skill.
-* Numbered options without a "skip" / "no change" path.
-* Steps that silently apply destructive changes — always show summary + ask.
-* Referring to `.augment/` paths for editing — source of truth is
-  `.agent-src.uncondensed/`.
-* Duplicating another command's workflow instead of delegating via `skills:`.
-
-## Frugality Standards
-
-Apply the [Frugality Charter](../../contexts/contracts/frugality-charter.md)
-to every command you author.
-
-**Examples in this artifact:**
-- Per the charter's default-terse rule, command output blocks state
-  the action result, not "Now we will execute…".
-- Per the post-action summary suppression, the success path emits
-  the artifact (PR URL, commit hash) without a wrapping summary.
-- Per the cheap-question check, never offer "preview vs. execute"
-  as a numbered option when the command's role is to execute.
-
-**Pre-save self-check:**
-1. Does any command step prescribe a "Let me…" or "Found it" output
-   line?
-2. Does the command default to multi-line summaries when a one-line
-   outcome suffices?
-3. Is a confirmation gate used outside the Iron-Law / Routine /
-   Contextual taxonomy?
-4. Are template placeholders (`{{var}}`) accompanied by setup prose
-   instead of action prose?
-
-## Do NOT
-
-* Do NOT set `disable-model-invocation: false`
-* Do NOT auto-apply destructive actions
-* Do NOT inline skill-level detail — delegate
-* Do NOT edit `.agent-src/`, `.augment/`, or `.claude/` projections
-* Do NOT exceed the hard size limit without a waiver
-
-## Cloud Behavior
-
-On cloud surfaces (Claude.ai Web, Skills API) the package's
-`scripts/skill_linter.py`, `scripts/condense.py`, and the `task`
-runner are not available. This skill still applies — but with
-prose-only validation:
-
-* Emit the full command file as a copyable Markdown block. Do not
-  attempt to write it to disk.
-* Self-check the frontmatter against the rules below — `name`,
-  `description`, `disable-model-invocation: true` MUST all be
-  present.
-* Self-check the body shape: numbered steps, explicit safety gates,
-  no inline skill-level detail.
-* Tell the user to save the file under
-  `.agent-src.uncondensed/commands/{name}.md` and run
-  `task sync && task lint-skills` locally before committing.
-* Skip every reference to running the linter, condenseor, or
-  generators yourself — they only run on the user's machine.
-
-## Examples
-
-Good description (trigger-shaped, outcome-focused):
-
-> "Create a GitHub PR with structured description from Jira ticket and code changes"
-
-Bad description (vague, no outcome):
-
-> "PR command"

package/.agent-src/skills/condense-memory/SKILL.md

@@ -1,123 +0,0 @@
----
-model_tier: inherit
-name: condense-memory
-description: "Use when shrinking always-loaded memory files (AGENTS.md, CLAUDE.md, .cursorrules) via telegraph grammar — refuses sensitive paths, round-trips via .original.md backup."
-domain: process
-execution:
-  type: assisted
-  handler: internal
-  allowed_tools: [Bash]
-workspaces:
-  - agent-config-maintainer
-packs:
-  - meta
----
-
-# condense-memory
-
-> **Experimental.** Output-side telegraph dialect did not meet kill-criterion in [`internal/bench/reports/telegraph-v1.md`](../../../bench/reports/telegraph-v1.md) (`vs_terse` median −9.27 %). Input-side memory condensation is orthogonal use case: savings target always-loaded memory budget, not reply stream. Treat ship-criterion as **per-target measurement**, not v1 verdict.
-
-## When to use
-
-Use when:
-
-- Always-loaded memory file (`AGENTS.md`, `CLAUDE.md`, `.cursorrules`, `GEMINI.md`, `.windsurfrules`) close to or above host tool's char budget and maintainer wants to recover input-token headroom.
-- Consumer-shipped `templates/AGENTS.md` failing `agents-md-thin-root` cap and pointer-extraction options exhausted.
-- Maintainer asks to "condense this memory file" or "shrink AGENTS.md" or names input-side telegraph.
-
-## Do NOT
-
-- Condense reply, commit message, PR body, ticket summary, or any deliverable written *for* human reader — those are carve-outs in [`telegraph-speak § Carve-outs`](../../rules/telegraph-speak.md) and stay verbatim.
-- Condense path matching sensitive-file denylist (`.env*`, `.netrc`, `credentials*`, `secrets*`, `id_rsa*`, `*.pem|key|p12|pfx|crt|cer|jks`, `.ssh/*`) — script refuses with `SensitivePathError` and so should you.
-- Condense generated file (`.agent-src/`, `.augment/`, `.claude/`, `.cursor/`, `.clinerules/`, `.windsurfrules`) — edit source in `.agent-src.uncondensed/` and regenerate via package's sync + generate-tools scripts (`scripts/condense.sh --sync` + `scripts/condense.py --generate-tools`).
-- Hand-edit condensed memory file in place — run `--decondense` first; next condense pass refuses on body-hash drift (`CondensationRefused`).
-- Commit condensed file without committing matching `.original.md` backup — round-trip breaks otherwise.
-
-## Procedure
-
-1. **Analyse target first.** Before any write, **inspect** target with `view` or `wc -l` to confirm it is always-loaded memory file (`AGENTS.md`, `CLAUDE.md`, `.cursorrules`, `GEMINI.md`, `.windsurfrules`), not generated, and has prose paragraphs to condense (pointer-only Thin-Root file may net near-zero). Skip rest of procedure if any check fails.
-2. **Check denylist gate.** Run `python3 scripts/condense_memory.py <path> --check` — exit 0 = safe; exit 2 = denylist hit, stop and surface refusal.
-3. **Record baseline.** `wc -c <path>` — capture pre-condensation char count for commit message.
-4. **Condense.** `python3 scripts/condense_memory.py <path>`. Script writes `<path>.original.md` (verbatim backup) and rewrites `<path>` with `original_sha256:` + `condensed_at:` frontmatter.
-5. **Inspect diff.** Eyeball every Iron-Law fence, numbered-options block, code fence, backtick span, `❌`/`⚠️`/`✅` line, and frontmatter pair — all must be byte-identical. Body prose may have lost articles (`the`/`a`/`an`) and auxiliaries (`is`/`are`/`was`/`be`/`that`/`which`).
-6. **Validate idempotency.** Re-run `python3 scripts/condense_memory.py <path>` — clean re-run is no-op (body hash matches). Non-zero exit = stop, escalate.
-7. **Commit both files together.** `<path>` and `<path>.original.md` ship as pair. Backup is rollback path; never commit one without other.
-8. **Rollback path.** If readability fails review at step 5: `python3 scripts/condense_memory.py <path> --decondense` restores backup and deletes `.original.md`.
-
-## Output format
-
-Maintainer-facing report after invoking script MUST contain, in this order:
-
-1. **Diff line** — pre/post `wc -c` as single line (`AGENTS.md: 2,891 → 2,453 chars (−15.1 %)`).
-2. **Backup path** — full path of `.original.md` backup so maintainer can verify it landed on disk.
-3. **Carve-out check** — one line confirming seven carve-out classes round-tripped (`carve-outs: 7 classes preserved · idempotent re-run: clean`).
-4. **Exit-code surface** — on failure, surface verbatim exit code and exception name (`SensitivePathError → exit 2`, `CondensationRefused → exit 3`, `FileNotFoundError → exit 4`); do not paraphrase.
-
-Do **not** narrate algorithm, grammar rules, or carve-out theory — rule and this skill document contract; output reports result.
-
-## Carve-outs — byte-for-byte preserved
-
-Mirrors seven carve-out classes in [`telegraph-speak`](../../rules/telegraph-speak.md). Condensation engine in [`scripts/condense_memory.py`](../../../scripts/condense_memory.py) preserves:
-
-1. **Triple-backtick fences** — any language, any depth.
-2. **Numbered-options lines** — `^>?\s*\d+\.\s` plus `**Recommendation:**` / `**Empfehlung:**` label.
-3. **Backtick spans** — file paths, command names, identifiers inside body prose.
-4. **Status / error markers** — lines starting with `❌`, `⚠️`, `✅`.
-5. **Iron-Law ALL-CAPS lines** — `^[A-Z][A-Z0-9 ,.\-_/']{3,}$`.
-6. **Frontmatter blocks** — `---` fence pairs at head of file.
-7. **Mode markers** per [`role-mode-adherence`](../../rules/role-mode-adherence.md).
-
-Mangling any of these breaks Iron-Law surface host tool reads. Unit tests in `tests/test_condense_memory.py` lock each carve-out class as regression case.
-
-## Idempotency contract — Step 9 guard
-
-Script is **idempotent on clean re-runs**: running it twice on same target is no-op because body hash matches recondensed hash. Script **refuses** on **body drift**:
-
-| State | Outcome |
-|---|---|
-| No frontmatter SHA marker | Condense + write backup + inject SHA. |
-| SHA marker present, body re-condenses to same hash | No-op (return target unchanged). |
-| SHA marker present, body hash diverged | **Refuse** with `CondensationRefused` exit 3. |
-
-If you need to edit condensed memory file, run `--decondense` first, edit restored `.original.md` content, then re-run condenseor. Never hand-edit condensed body — next CI run will either silently corrupt your edit (if it happens to re-condense to same shape) or hard-fail next condense pass.
-
-## Sensitive-path gate
-
-Every read path passes through [`scripts/validate_safe_paths.py`](../../../scripts/validate_safe_paths.py) `assert_safe()` before bytes leave disk. Gate is security floor for Phase 2 (input-side condensation) per `step-16-telegraph-substance.md` Phase 0; rollback of gate is rollback of this skill.
-
-CLI exit codes:
-
-- `0` — condense / decondense / check succeeded.
-- `2` — `SensitivePathError` (path matched denylist).
-- `3` — `CondensationRefused` (body hash diverged from frontmatter SHA).
-- `4` — `FileNotFoundError` (no `.original.md` backup to restore).
-
-## Gotchas
-
-- **Body-hash drift after manual edit** — hand-editing condensed body breaks `original_sha256:` invariant. Next condense pass refuses with `CondensationRefused` (exit 3). Recovery: `--decondense`, edit restored body, re-condense.
-- **`.original.md` backup missing on `--decondense`** — exit 4 (`FileNotFoundError`). Either someone deleted backup or `--decondense` already ran. Restore from git history; never regenerate backup by hand (regenerated content would not be byte-identical).
-- **Denylist false positive** — sensitive-looking filename outside denylist surface (project-specific naming) will still pass `assert_safe()`. Denylist necessary but not sufficient; maintainer responsible for never feeding secrets to condenseor.
-- **Frontmatter ordering with existing keys** — if target already has frontmatter, condenseor preserves existing keys, drops any prior `original_sha256:` / `condensed_at:` entries, and appends new pair. Other agents reading file should treat SHA + timestamp pair as canonical condensation marker, not file size.
-- **Negative savings on pointer-heavy files** — `templates/AGENTS.md` already following Thin-Root (≥ 40 % pointers, ≥ 60-char *why*-clauses) has little prose left to drop; condensation may net near-zero or even add bytes via frontmatter. Run [`agents-md-thin-root`](../agents-md-thin-root/SKILL.md) first to maximise pointer share, then measure whether this skill still pays.
-- **Generated-tree drift** — condensing `.agent-src.uncondensed/templates/AGENTS.md` does NOT propagate to `.augment/`, `.claude/`, etc. until package's sync + generate-tools scripts run (`scripts/condense.sh --sync` + `scripts/condense.py --generate-tools`). Always regenerate after condensing templated file.
-
-## Measurement — when to condense
-
-No published `telegraph-v2` baseline for input-side savings yet (Step 11 of `step-16-telegraph-substance.md` ships that). Until then, maintainer judges per-target whether condensation pays its readability cost. Suggested workflow:
-
-1. `wc -c <path>` before — record baseline char count.
-2. `python3 scripts/condense_memory.py <path>` — condense + back up.
-3. `wc -c <path>` after — record post-condensation char count.
-4. Eyeball diff: does prose stay legible? Are all Iron-Law fences intact?
-5. If yes → commit both `<path>` and `<path>.original.md`. If no → `--decondense`.
-
-Future `telegraph-v2.md` will tabulate realised input-token saving against `agents-md-thin-root` 40 % pointer-ratio constraint so maintainer has numerical floor.
-
-## Cross-references
-
-- [`telegraph-speak`](../../rules/telegraph-speak.md) — runtime rule script mirrors for input-side targets; `telegraph.speak_scope` does **not** gate this script (input-side runs regardless).
-- [`scripts/validate_safe_paths.py`](../../../scripts/validate_safe_paths.py) — Phase 0 gate; ported from upstream Telegraph `63a91ec`.
-- [`scripts/condense_memory.py`](../../../scripts/condense_memory.py) — implementation.
-- [`tests/test_condense_memory.py`](../../../tests/test_condense_memory.py) — regression locks for each carve-out + idempotency + denylist.
-- [`docs/contracts/condensation-default-kill-criterion.md`](../../../docs/contracts/condensation-default-kill-criterion.md) — v1 verdict (output-side; informs but does not gate this skill).
-- [`agents-md-thin-root`](../agents-md-thin-root/SKILL.md) — caps consumer-shipped `templates/AGENTS.md`; this skill is one tool to land under cap.

package/.agent-src/skills/context-document/SKILL.md

@@ -1,160 +0,0 @@
----
-model_tier: inherit
-name: context-document
-description: "Use when the user says "create context", "document this area", or wants a structured snapshot of a codebase area for agent orientation."
-domain: process
-workspaces:
-  - agent-config-maintainer
-packs:
-  - meta
----
-
-# context
-
-## When to use
-
-Use this skill when:
-- Documenting a module, service, or integration for future reference
-- Exploring an unfamiliar area of the codebase
-- Preparing for a feature that touches multiple areas
-- Onboarding to a new part of the codebase
-
-
-Do NOT use when:
-- Writing code or features
-- Creating roadmaps (use `roadmap-management` skill)
-
-## Procedure: Manage contexts
-
-1. **Identify scope** — Which area of the codebase needs a context document?
-2. **Research** — Use codebase-retrieval to understand the area (files, patterns, dependencies).
-3. **Write or update** — Create/update the context doc following the template below.
-4. **Verify** — Confirm all referenced files exist and descriptions match current code.
-
-A **context document** is a structured snapshot of a codebase area:
-- What it does, why it exists
-- Key files, classes, and patterns
-- Database tables and API endpoints
-- Dependencies and known issues
-
-Unlike feature plans (future-focused) or roadmaps (task-focused), contexts are
-**present-focused** — they describe the current state of the code.
-
-## File structure
-
-```
-.augment/contexts/                       # Shared contexts (about the agent system itself)
-├── augment-infrastructure.md
-├── skills-and-commands.md
-└── documentation-hierarchy.md
-
-agents/settings/contexts/                         # Project-wide contexts
-├── {context-name}.md
-
-{module_root}/{Module}/{agent_folder}/settings/contexts/ # Module-scoped contexts
-├── {context-name}.md                                    # Laravel: app/Modules/…
-                                                         # Symfony: src/Bundle/…
-                                                         # Monorepo: packages/…
-
-.augment/templates/
-└── contexts.md                          # Context template
-```
-
-## Context types
-
-| Type | Scope | Example |
-|---|---|---|
-| **Module** | Single module's structure and purpose | `client-software.md` |
-| **Domain** | Business domain across modules | `import-pipeline.md` |
-| **Service** | Complex service with its deps | `customer-service.md` |
-| **Integration** | External API/system integration | `probaus-api.md` |
-| **Infrastructure** | DevOps or infrastructure concern | `queue-system.md` |
-
-## Where to store contexts
-
-| Content | Location |
-|---|---|
-| About the `.augment/` system itself | `.augment/contexts/` (shared package) |
-| Project-wide or cross-module | `agents/settings/contexts/` |
-| Module-specific | `{module_root}/{Module}/{agent_folder}/settings/contexts/` (resolved via `modules.root_paths` + `modules.agent_folder`; Laravel example: `app/Modules/{Module}/agents/settings/contexts/`) |
-| If unsure | Ask the user |
-
-### Shared vs. project-specific contexts
-
-**`.augment/contexts/`** — Part of the shared package. Describes the agent infrastructure:
-how overrides work, what skills/commands exist, the documentation hierarchy.
-These are read-only at project level (like all `.augment/` content).
-
-**`agents/settings/contexts/`** — Project-specific. Describes the project's business domain:
-modules, services, integrations, database architecture.
-These are created and maintained per project.
-
-## Integration with other systems
-
-### Sessions
-When working in an area that has a context document, load it at session start.
-The session's Context section can reference it.
-
-### Features
-Before planning a feature, check if a context document exists for the affected area.
-It provides the baseline understanding needed for planning.
-
-### Module exploration
-`/module-explore` gathers the data needed to create a module context.
-`/context-create` turns that exploration into a persistent document.
-
-### Overrides
-When customizing a shared skill or command, read `.augment/contexts/override-system.md` for the naming conventions and format.
-
-### Shared contexts
-When working on the agent infrastructure itself (skills, commands, rules), check
-`.augment/contexts/` for existing documentation about the system.
-
-## Behavior rules
-
-### Creating contexts
-
-1. **Always analyze the code first** — use `codebase-retrieval`, `view`, and file listing.
-2. **Be factual** — describe what IS, not what SHOULD be.
-3. **Be specific** — link to files, name classes, reference tables.
-4. **Ask the user** about anything unclear.
-
-### Maintaining contexts
-
-- Update `Last Updated` when modifying.
-- When code changes affect a context, update it.
-- `/context-refactor` is the dedicated command for this.
-
-## Commands
-
-| Command | Purpose |
-|---|---|
-| `context-create` | Analyze an area and create a new context document |
-| `context-refactor` | Revisit, update, and extend an existing context |
-
-
-## Output format
-
-1. Context document in the correct location with structured sections
-2. Cross-references to related contexts updated
-
-## Auto-trigger keywords
-
-- context document
-- codebase context
-- orientation doc
-- context creation
-
-## Gotcha
-
-- Context docs become stale — always check the actual code before trusting a context document.
-- Don't create context docs for areas that change weekly — they'll be outdated immediately.
-- Keep context docs factual, not aspirational — document what IS, not what should be.
-
-## Do NOT
-
-- Do NOT create contexts without analyzing the code first.
-- Do NOT guess about architecture — verify by reading the code.
-- Do NOT duplicate information from `AGENTS.md` — reference it instead.
-- Do NOT commit or push without permission.
-- Do NOT create contexts for trivial areas — only when the knowledge is worth persisting.