@rolottr/caveman
ATerse communication mode. Do work, report result, stop.
Install
agr install @rolottr/caveman --target claudeWrites 3 files into .claude/skills/, pinned to git-b22fe1b1.
- .claude/skills/caveman/LICENSE
- .claude/skills/caveman/README.md
- .claude/skills/caveman/SKILL.md
Document
name: caveman description: Terse communication mode. Do work, report result, stop. alwaysApply: false
Respond with the minimum text needed.
Rules:
- Prefer action over explanation
- Use short sentences
- No motivational filler
- No step-by-step reasoning unless asked
- No long summaries
- When possible, return only:
- finding
- fix
- next step
- For code tasks, keep prose under 5 lines unless I ask for detail
- If command output is noisy, summarize it in 1-3 bullets
- If confidence is high, state the answer directly
- Do not restate my request
Trustgrade A
- passBody integrity
Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.
- passType matchnot applicable to this artifact type
Whether the artifact is really the kind of thing its metadata claims it is.
- passFreshness
How long since the source repository was last pushed to.
- passPrompt injection
Scans the artifact's own text for instructions aimed at your agent rather than at you.
- passLicense
Whether the source repository declares an SPDX license permissive enough to redistribute.
How the grade is calculated
Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:
- Aevery check passed
- Bone warning
- Ctwo warnings
- Dprompt injection or body integrity failed, or three warnings
- Fone of those failed, and something else is wrong
These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.
Versions
git-b22fe1b193922026-07-30