Individual skill
click
Record revision-aware evidence for software work by default, or bind higher-risk execution to one human-readable approval contract in Guarded mode. Use when Click Hook context enables Evidence or Guarded mode, or when the user explicitly selects Click. Do not use for questions or explanations.
plugins/grapefruit0205/click/skills/click/SKILL.md
Source commit d780783eba4ecc7c8b9429f95c9362df95f07c61
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 4, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 1,532
- Repository last updated
- Nov 6, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai-coding Repository topic
- awesome Repository topic
- awesome-list Repository topic
- codex Repository topic
- codex-plugins Repository topic
- openai Repository topic
- codex-skill Repository topic
- codex-skills Repository topic
- marketplace Repository topic
- codex-marketplace Repository topic
- engineering Derived category
- legal Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 6,706 bytesagents/openai.yamlasset · 407 bytesreferences/anti-loop-policy.mddoc · 7,917 bytesreferences/antigravity.mddoc · 3,332 bytesreferences/authoritative-observer-v2.mddoc · 12,845 bytesreferences/automatic-sharding-setup.mddoc · 13,259 bytesreferences/capability-protocol.mddoc · 38,310 bytesreferences/claude-code.mddoc · 2,693 bytesreferences/directive-format.mddoc · 8,233 bytesreferences/evidence-shards-v1.mddoc · 6,722 bytesreferences/guarded-mode.mddoc · 10,585 bytesreferences/modes.mddoc · 8,306 bytesreferences/observer-v1.mddoc · 11,862 bytesreferences/shadow-intelligence-v1.mddoc · 7,436 bytesreferences/translation-guide.mddoc · 4,983 bytesreferences/verification-efficiency.mddoc · 3,583 bytesreferences/verification-profiles.mddoc · 10,614 bytes
Read excerpt
# Click
Click is an incremental-verification runtime. In **Evidence** mode, the default, the host authorizes work exactly as it normally does; Click records what happened and decides which checks must run again. Do not treat a question about Click as a mutation, and do not stage a contract or ask for Click approval in Evidence mode.
## What Click records on its own
- The user prompt becomes the intent lineage of the Evidence session. An in-scope or narrowing follow-up continues it; the next request after a completed session starts a fresh one. A fresh session, including a new Claude Code session of the same repository, starts from the archived receipts of the last completed one; Click requalifies them, so do not re-run a check only because the session is new.
- Every recognized file edit and every `click-gate mutate` advances the mutation revision, which invalidates earlier receipts.
- Every check submitted through `click-gate verify` gets an exact receipt bound to its argv, revision, protected tree, environment, executable, and host coverage. Supported checks also capture their inputs automatically.
None of this needs a contract, an approval, or a dependency declaration from you. Never invent one, and never create, widen, or edit `.click/evidence-reuse.json` or a shard map to skip a check.
## Run checks through `click-gate verify`