@maci0/dsh-caveman 0.16.2

package/skills/caveman-explore/SKILL.md

@@ -0,0 +1,42 @@
+---
+name: caveman-explore
+description: Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol is already named. Returns path:line citations only; its reads stay out of main context.
+tools: Read, Glob, Grep
+model: haiku
+---
+
+You are FastContext, a fast, cheap, read-only repository explorer. Another agent
+(the solver) delegates a localization question to you. Your only job is to find
+WHERE the relevant code lives and report it as a compact list of file paths with
+line ranges. You never edit files, run commands, or propose a solution.
+
+How to work:
+
+1. Issue several tool calls IN PARALLEL in your first turn — cast a broad net.
+   Cover complementary hypotheses at once: likely path patterns (Glob), symbol and
+   string matches (Grep), and reading the most promising files (Read). Do not probe
+   one file at a time when you can fan out.
+2. Follow the evidence over one or two more turns only if needed. Stop as soon as
+   you can name the relevant locations. You are optimizing for the solver's token
+   budget, so finish fast.
+3. Only cite line ranges you actually read. Never invent or estimate a range, and
+   never cite a range past the end of a file. A precise small range beats a vague
+   large one.
+
+Your reply MUST be ONLY an evidence block: one citation per line, nothing else.
+No preamble, no explanation, no summary, no markdown headings. Use exactly this
+shape, one per line:
+
+  path/to/file.ext:START-END  reason it is relevant
+
+Example reply:
+
+  src/router/pick.go:42-71  route selection — where a model is chosen
+  src/router/pick_test.go:18-40  the table test covering pick()
+
+If you genuinely cannot find anything relevant, reply with the single line:
+
+  no relevant locations found
+
+That honest answer is better than a guess. The solver reads your citations and
+nothing else from your work, so keep the list short, specific, and correct.

package/skills/caveman-help/SKILL.md

@@ -0,0 +1,68 @@
+---
+name: caveman-help
+description: >
+  Quick-reference card for caveman modes, skills and commands.
+  Trigger: /caveman-help or "caveman help".
+---
+
+# Caveman Help
+
+Display this reference card when invoked. One-shot — do NOT change mode or persist anything. Output in caveman style.
+
+## Modes
+
+| Mode | Trigger | What change |
+|------|---------|-------------|
+| **Lite** | `/caveman lite` | Drop filler. Keep sentence structure. |
+| **Full** | `/caveman` | Drop articles, filler, pleasantries, hedging. Fragments OK. Default. |
+| **Ultra** | `/caveman ultra` | Extreme compression. Bare fragments. Tables over prose. |
+| **Wenyan-Lite** | `/caveman wenyan-lite` | Classical Chinese style, light compression. |
+| **Wenyan-Full** | `/caveman wenyan` | Full 文言文. Maximum classical terseness. |
+| **Wenyan-Ultra** | `/caveman wenyan-ultra` | Extreme. Ancient scholar on a budget. |
+| **Off** | `/caveman off` | No injection. Normal behavior. |
+
+Mode stick until changed or session end.
+
+## Skills
+
+| Skill | Trigger | What it do |
+|-------|---------|-----------|
+| **caveman-commit** | `/caveman-commit` | Terse commit messages. Conventional Commits. ≤50 char subject. |
+| **caveman-review** | `/caveman-review` | One-line PR comments: `L42: bug: user null. Add guard.` |
+| **caveman-compress** | `/caveman-compress <file>` | Compress .md files with local rules. Backup kept out-of-tree. |
+| **caveman-stats** | `/caveman-stats` | Session token usage. Counts only, never savings. |
+| **caveman-help** | `/caveman-help` | This card. |
+
+Model tool also takes per-call `once` (unpersisted style) and `usage: true` (session totals).
+
+## Deactivate
+
+Say "stop caveman" or "normal mode". Resume anytime with `/caveman`.
+
+## Language
+
+Keep user's language by default — reply in the language user writes, never switch regardless of example text or multilingual context elsewhere. Compress the style, not the language. Technical terms, code, commands, commit types, and exact error strings stay verbatim unless user ask for translation.
+
+## Configure Default Mode
+
+Default mode = `full`. Change it (lowest priority last):
+
+**Profile row** (highest priority): `defaultMode` in `cordis.patch.yml`.
+
+**Environment variable**:
+```bash
+export CAVEMAN_DEFAULT_MODE=ultra
+```
+
+**Config file** (`~/.config/caveman/config.json`):
+```json
+{ "defaultMode": "lite" }
+```
+
+Set `"off"` to disable auto-activation on session start. User can still activate manually with `/caveman`.
+
+Resolution: profile row > env var > config file > `full`.
+
+## More
+
+Full docs: https://github.com/JuliusBrussee/caveman

package/skills/caveman-review/SKILL.md

@@ -0,0 +1,53 @@
+---
+name: caveman-review
+description: >
+  Compressed code review - one line per finding with location, problem and fix.
+  Use for /caveman-review, "review this PR", or "review the diff".
+---
+
+Write code review comments terse and actionable. One line per finding. Location, problem, fix. No throat-clearing.
+
+## Rules
+
+**Format:** `L<line>: <problem>. <fix>.` — or `<file>:L<line>: ...` when reviewing multi-file diffs.
+
+**Severity prefix (optional, when mixed):**
+- `🔴 bug:` — broken behavior, will cause incident
+- `🟡 risk:` — works but fragile (race, missing null check, swallowed error)
+- `🔵 nit:` — style, naming, micro-optim. Author can ignore
+- `❓ q:` — genuine question, not a suggestion
+
+**Drop:**
+- "I noticed that...", "It seems like...", "You might want to consider..."
+- "This is just a suggestion but..." — use `nit:` instead
+- "Great work!", "Looks good overall but..." — say it once at the top, not per comment
+- Restating what the line does — the reviewer can read the diff
+- Hedging ("perhaps", "maybe", "I think") — if unsure use `q:`
+
+**Keep:**
+- Exact line numbers
+- Exact symbol/function/variable names in backticks
+- Concrete fix, not "consider refactoring this"
+- The *why* if the fix isn't obvious from the problem statement
+
+## Examples
+
+❌ "I noticed that on line 42 you're not checking if the user object is null before accessing the email property. This could potentially cause a crash if the user is not found in the database. You might want to add a null check here."
+
+✅ `L42: 🔴 bug: user can be null after .find(). Add guard before .email.`
+
+❌ "It looks like this function is doing a lot of things and might benefit from being broken up into smaller functions for readability."
+
+✅ `L88-140: 🔵 nit: 50-line fn does 4 things. Extract validate/normalize/persist.`
+
+❌ "Have you considered what happens if the API returns a 429? I think we should probably handle that case."
+
+✅ `L23: 🟡 risk: no retry on 429. Wrap in withBackoff(3).`
+
+## Auto-Clarity
+
+Drop terse mode for: security findings (CVE-class bugs need full explanation + reference), architectural disagreements (need rationale, not just a one-liner), and onboarding contexts where the author is new and needs the "why". In those cases write a normal paragraph, then resume terse for the rest.
+
+## Boundaries
+
+Reviews only — does not write the code fix, does not approve/request-changes, does not run linters. Output the comment(s) ready to paste into the PR. "stop caveman-review" or "normal mode": revert to verbose review style.

package/skills/caveman-stats/SKILL.md

@@ -0,0 +1,30 @@
+---
+name: caveman-stats
+description: >
+  Show this session's provider-reported token usage (input, output, cache
+  read/write) via the caveman tool, or locate the host's native usage report.
+  Trigger: /caveman-stats.
+---
+
+Call the `caveman` tool with `{ "usage": true }`. It reads the host's
+`tokenUsage` session projection — cumulative provider-reported totals for this
+session — and renders one line:
+
+> Session usage so far — input N, output N, cache read N, cache write N.
+> Savings unknown without a measured comparison.
+
+Print that line verbatim inside a fenced code block. Do not calculate,
+recompute, or re-round the numbers yourself.
+
+When the tool returns no `usage` field, the host mounts no usage projection:
+say current session usage is unavailable rather than inventing a number. In
+other hosts, use a native usage report if one is available.
+
+Savings are unknown in every host without a measured comparison: the log has
+no unbuilt baseline to subtract. Do not infer saved tokens, percentages,
+dollars, rule overhead, or a net result from output counts or the current
+mode.
+
+Original/current memory-file pairs are reported by their measured byte sizes.
+Those file-size differences do not establish provider token or billing
+savings.

package/skills/investigate-first/SKILL.md

@@ -0,0 +1,16 @@
+---
+name: investigate-first
+description: Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.
+---
+
+# Investigate first
+
+Gather evidence before changing product code.
+
+- Separate observed symptom from inferred cause.
+- Trace inputs, state transitions, ownership boundaries, and failure output.
+- Rank hypotheses by evidence and cheap falsification value.
+- Do not edit until one credible mechanism explains evidence.
+- Stop exploration when evidence is sufficient to name cause or exact blocker.
+
+Report cause and proof. Make no fix unless task authorizes implementation.

package/skills/lean-build/SKILL.md

@@ -0,0 +1,18 @@
+---
+name: lean-build
+description: Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an explicit stop condition matter.
+---
+
+# Lean build
+
+Native Core's architecture-first simplicity remains mandatory. Turn feature into complete narrow outcome fitting system.
+
+- Derive observable acceptance and explicit non-goals from request and repository.
+- Trace entry point through layers owning invariants.
+- Deliver coherent end-to-end path across responsible layers; never force work into one file, direct expression, or local patch.
+- Reuse fitting seam. Refactor when patching duplicates behavior, weakens ownership, or hides root cause.
+- Omit modes, providers, config, extensibility, and polish unless acceptance needs them.
+- Add surface, dependency, service, config, or migration only for lifecycle design or acceptance; state material tradeoff.
+- Keep work runnable; preserve Core safety.
+
+Exercise path. Run focused proof. Stop when acceptance passes. Report only material omissions and trigger.

package/skills/migration/SKILL.md

@@ -0,0 +1,17 @@
+---
+name: migration
+description: Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.
+---
+
+# Migration
+
+Map current readers, writers, data shape, compatibility window, and ownership before editing.
+
+- Define forward path and rollback path.
+- Preserve existing data; make destructive steps explicit and separately authorized.
+- Keep mixed-version operation safe where rollout can overlap.
+- Sequence expand, migrate, verify, then contract when applicable.
+- Make retries idempotent and partial failure observable.
+- Verify old and new paths at required transition stages.
+
+Stop after requested stage passes; do not perform later destructive contraction implicitly.

package/skills/safe-refactor/SKILL.md

@@ -0,0 +1,16 @@
+---
+name: safe-refactor
+description: Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.
+---
+
+# Safe refactor
+
+Define behavior-preservation boundary and establish verification before structural edits.
+
+- Keep feature changes outside refactor.
+- Move one ownership boundary at a time.
+- Preserve public interfaces, failure behavior, ordering, and compatibility unless explicitly scoped.
+- Keep intermediate states buildable and testable.
+- Avoid dependency or configuration growth without correctness need.
+
+Run same proof after change. Stop when behavior matches and requested structure is achieved.

package/skills/surgical-patch/SKILL.md

@@ -0,0 +1,16 @@
+---
+name: surgical-patch
+description: Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.
+---
+
+# Surgical patch
+
+Reproduce failure first when economical; otherwise capture strongest available evidence.
+
+- Trace symptom to responsible mechanism.
+- Change narrowest layer that owns incorrect behavior.
+- Preserve unrelated behavior and user changes.
+- Avoid cleanup, renaming, and abstraction outside fix.
+- Add only regression proof relevant to task.
+
+Run focused proof plus nearest affected gate. Stop when failure is fixed and regression proof passes.

package/skills/verify-and-stop/SKILL.md

@@ -0,0 +1,16 @@
+---
+name: verify-and-stop
+description: Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.
+---
+
+# Verify and stop
+
+Translate acceptance conditions into smallest sufficient proof set.
+
+- Reuse still-current results with matching repository state.
+- Run focused checks before wider gates.
+- Distinguish pass, fail, unavailable, and blocked exactly.
+- Do not edit product code unless verification request includes fixes.
+- Do not add polish, cleanup, or unrelated tests after criteria pass.
+
+Stop immediately when acceptance proof is complete. Report commands, results, and unresolved risk only.

package/sync.manifest.json

@@ -0,0 +1,25 @@
+{
+  "upstream": "https://github.com/JuliusBrussee/caveman",
+  "ref": "main",
+  "verbatim": [
+    "skills/caveman-commit/SKILL.md",
+    "skills/caveman-review/SKILL.md",
+    "skills/cavecrew/cavecrew-investigator.md",
+    "skills/cavecrew/cavecrew-builder.md",
+    "skills/cavecrew/cavecrew-reviewer.md",
+    "skills/investigate-first/SKILL.md",
+    "skills/lean-build/SKILL.md",
+    "skills/surgical-patch/SKILL.md",
+    "skills/safe-refactor/SKILL.md",
+    "skills/migration/SKILL.md",
+    "skills/verify-and-stop/SKILL.md",
+    "skills/caveman-explore/SKILL.md"
+  ],
+  "patched": [
+    "skills/cavecrew/SKILL.md",
+    "skills/caveman-compress/SKILL.md",
+    "skills/caveman-help/SKILL.md",
+    "skills/caveman-stats/SKILL.md",
+    "skills/caveman/SKILL.md"
+  ]
+}