caveman-manage
Skill0 starsChanged 10 days agoMITView on GitHub
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.
11 other projects use a version of this, 6 of them edited.
How people change it
All 5 edited versions we compared keep every one of its 10 rules.
Of the 5 edited versions we compared: 5 keep every rule.
We split this file and each edited version into the rules they give an agent and match them by wording. A version that adds no rule of its own and has not changed since this file last did reads as an older text, so what it lacks is not counted as dropped. We keep no past texts of a file, so that is inferred, and an edited version that started from an older text still counts its gaps as drops.
Adopted by
Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data
Most recently taken up by
- gameyfin/gameyfinword for word, first seen Nov 16, 2026
- mjlueck-hash/cavemanedited, first seen Nov 8, 2026
- MMACABRE/SKILLSword for word, first seen Nov 8, 2026
- jjsizemore/jjskillsedited, first seen Nov 1, 2026
- pengawasmknan/claude-skillsword for word, first seen Oct 11, 2026
- Gopyr/gopyr-skills-hubedited, first seen Oct 11, 2026
Other versions11 projects use a version of this.
Word for word · 5
- JuliusBrussee/caveman★ 120k100% same
- gameyfin/gameyfin★ 1.2k100% same
- nomdedev/agent-manager-template★ 2100% same
- MMACABRE/SKILLS★ 1100% same
- pengawasmknan/claude-skills★ 0100% same
Edited · 6
- Youngmaidainon/Agent-Level-Up★ 393% same
- xingtu1996/dsh-xingtu-skills★ 293% same
- jjsizemore/jjskills★ 193% same
- mjlueck-hash/caveman★ 193% same
- Gopyr/gopyr-skills-hub★ 050% same
- xingtu1996/xingtu-skills★ 093% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository46 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/caveman-learn/CLAUDE.mdCLAUDE.md
- brainstormingSkill
- cavecrewSkill
- caveman-commitSkill
- caveman-compressSkill
- caveman-discoverSkill
- caveman-evidence-reviewSkill
- caveman-exploreSkill
- caveman-helpSkill
- caveman-learnSkill
- caveman-optimizeSkill
- caveman-reviewSkill
- caveman-setupSkill
- cavemanSkill
- caveman-statsSkill
- diagnosing-superpowersSkill
- dispatching-parallel-agentsSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- handoffSkill
- investigate-firstSkill
- karpathy-extendedSkill
- lean-buildSkill
- mcp-builderSkill
- megacaveSkill
- migrationSkill
- plugin-doctorSkill
- receiving-code-reviewSkill
- requesting-code-reviewSkill
- safe-refactorSkill
- scholastic-disputationSkill
- socratic-inquirySkill
- subagent-driven-developmentSkill
- surgical-patchSkill
- systematic-debuggingSkill
- terrasharkSkill
- test-driven-developmentSkill
- ultracaveSkill
- using-foundational-thinkingSkill
- using-git-worktreesSkill
- using-superpowersSkill
- verification-before-completionSkill
- verify-and-stopSkill
- writing-plansSkill
- writing-skillsSkill
The file
We split this skill into the rules it gives an agent
10 rules. 7 are common, 0 are distinctive, and 3 are very specific to this project.
7
Common
Most of the 5 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Common: line 11
Treat every lifecycle change as a production control action.
- Common: line 19
Never approve an experiment whose results are pending, whose required guardrails are absent, or whose evidence reports a breach.
- Very specific: line 21
Never convert experiment lift into verified_savings.
- Common: line 23
Never supply an organization id.
- Very specific: line 25
Never execute a lifecycle mutation, even after user approval.
- Very specific: line 41
Use {"action":"list"} when the user has not named an id.
- Common: line 51
Stop if login, project, experiment, or results are unavailable.
- Common: line 88
Do not treat earlier generic statements such as "manage it" or "do what is best" as mutation approval.
- Common: line 93
Do not emit or run an executable lifecycle command.
- Common: line 99
If operator says they executed command, read detail and results again.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Manage eval-gated experiments
Treat every lifecycle change as a production control action. Read current state and results, then report one supported recommendation or block. Current agent MCP is intentionally read-only: control-api does not yet enforce a complete lifecycle transition table and evidence gate atomically.
Non-negotiable gates
- A request to review, inspect, explain, or recommend authorizes reads only.
- Never approve an experiment whose results are pending, whose required guardrails are absent, or whose evidence reports a breach.
- Never convert experiment lift into
verified_savings. Only active real traffic plus provider-causal, provider-complete ledger evidence can do that. - Never supply an organization id. Project and tenant scope come from the logged-in Caveman identity and server RBAC.
- Never execute a lifecycle mutation, even after user approval. Exact
<action>:<experiment_id>strings are agent-generatable and are not proof of human intent. - Unknown states and server errors fail closed. Report exact
cave_snake_code.
Step 1 — Load project and experiment
Prefer MCP:
caveman_context {}
caveman_experiment_get {"action":"get","experiment_id":"<id>"}
caveman_experiment_get {"action":"results","experiment_id":"<id>"}Use {"action":"list"} when the user has not named an id.
CLI fallback:
caveman cloud experiments list
caveman cloud experiments show <id>
caveman cloud experiments results <id>Stop if login, project, experiment, or results are unavailable.
Step 2 — Evaluate evidence
Report:
- current lifecycle state and safety class;
- control and candidate sample sizes;
- quality or eval result;
- latency, error, cost, retry, drop, and escalation guardrails when present;
- evidence cost;
- rollback or hold reason;
- whether result is pending, failed, promotable, or active.
Absence is not a pass. If a required field is absent, state
evidence incomplete and do not propose approval.
Step 3 — Propose one action
Allowed actions:
start— only from a startable draft or queued state with configured graders;approve— only with complete passing evidence and a safety class the current role may approve;cancel— stop a non-active experiment the user no longer wants;rollback— revert an active or harmful change through the server's linked policy path. Current deployments may reject this honestly withcave_not_implemented; never describe that response as a rollback.
Show recommendation and id:
Proposed action: approve experiment 7f...
Reason: candidate passed quality and every configured guardrail.
Execution: blocked until server-authoritative lifecycle and evidence gates ship.Do not treat earlier generic statements such as "manage it" or "do what is best" as mutation approval.
Step 4 — Block unsafe execution
Do not emit or run an executable lifecycle command. Explain that current server does not yet enforce every evidence/state transition atomically. CLI and MCP agent surfaces therefore expose experiment reads only.
Step 5 — Re-read after external operator action
If operator says they executed command, read detail and results again. Report server-observed post-state, audit or result response, and any policy-delivery status returned. Never infer success from operator intent alone.
Use this close:
Action: <action> <experiment-id>
Before: <state>
Server response: <status and cave_snake_code if any>
After: <re-read state>
Basis: experiment evidence only. Verified savings unchanged unless the signed
ledger independently records active, provider-causal real-traffic savings.Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

