agents-judgment-calls-gate
Skill3 starsChanged 4 days agoMITView on GitHub
Review a judgment call before it counts. Require both options, the caller's own prior, and local evidence when the choice follows an agent lean. Anthropic's study rates stay theirs.
In this repository153 other files it gives its agents.
- AGENTS.mdAGENTS.md
- hermes-mobile/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/agent-automations.mdcCursor rule
- .cursor/rules/agent-device.mdcCursor rule
- .cursor/rules/agent-harness-router.mdcCursor rule
- .cursor/rules/agent-skills-overview.mdcCursor rule
- .cursor/rules/always-agent-mode.mdcCursor rule
- .cursor/rules/callstack-agent-skills-overview.mdcCursor rule
- .cursor/rules/callstack-react-native-best-practices.mdcCursor rule
- .cursor/rules/codeql-agent-hygiene.mdcCursor rule
- .cursor/rules/decision-stack.mdcCursor rule
- .cursor/rules/expo-credit-budget.mdcCursor rule
- .cursor/rules/fleet-repo-intelligence.mdcCursor rule
- .cursor/rules/hermes-mobile-prevention-july-2026.mdcCursor rule
- .cursor/rules/hermes-mobile-real-users.mdcCursor rule
- .cursor/rules/hermes-mobile-verification.mdcCursor rule
- .cursor/rules/no-desktop-hijack.mdcCursor rule
- .cursor/rules/no-manual-handoffs.mdcCursor rule
- .cursor/rules/obsidian-teammate-collaboration.mdcCursor rule
- .cursor/rules/prefer-headless-background-ops.mdcCursor rule
- .cursor/rules/react-native-best-practices.mdcCursor rule
- public/llms.txtllms.txt
- advertise-thumbgate-github-marketplaceSkill
- agent-harness-routerSkill
- agentic-pattern-selectorSkill
- ai-native-sdlcSkill
- android-dev-summit-26-gateSkill
- anti-babysitting-mandateSkill
- anti-babysittingSkill
- background-agent-hold-gateSkill
- browseros-agent-harnessSkill
- webmcp-agent-readinessSkill
- ci-first-failSkill
- ci-pr-monitorSkill
- cloudflare-developer-stackSkill
- cloudflare-kitesurf-browserSkill
- cloudflare-monetization-gatewaySkill
- confidence-offer-gateSkill
- content-laneSkill
- context-six-blockSkill
- context-vaultSkill
- context-weight-gateSkill
- dual-model-agentic-graphragSkill
- egm-fresh-reviewSkill
- elevenlabs-voice-agentsSkill
- emeans-quant-and-instinctSkill
- explainx-trending-honestSkill
- explainx-trending-ragSkill
- future-agi-self-healing-engineSkill
- garryslist-opportunity-trackerSkill
- gemini-decisions-hold-gateSkill
- git-at-scaleSkill
- gitbutler-fleet-automationsSkill
- gitbutler-google-ssoSkill
- gitbutler-mcp-isolatedSkill
- gitbutler-session-absorbSkill
- git-hooks-no-huskySkill
- github-marketplace-action-publishSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this before a merge, a send, a spend, a delete, a ship, or a recommendation is treated as decided.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Judgment-call review
Use this before a merge, a send, a spend, a delete, a ship, or a recommendation is treated as decided.
Anthropic's write-up is the source: https://www.anthropic.com/research/agents-judgment-calls
Experts in that study signed work whose open choices had followed an agent's lean, and many of them later repeated the agent's wording. Their rates stay theirs. This gate does not call a model and does not store a deferral rate.
What this gate does
- A judgment names two different options and a case for each.
- The caller records their own prior: A, B, or none.
- The caller records the agent lean: A, B, or none.
- A choice that follows the lean needs local evidence, and that evidence has to be something other than the agent's paragraph.
- Switching off a stated prior onto the lean needs a credit.
- A reason that repeats the agent's wording needs a credit.
- A second check that names the same model as the first is blocked.
- A routine typo is left alone.
- A review with no task stays blocked. A rollout recommendation is a judgment.
- A local success rate is a study claim only when the same text attributes it to the study.
Commands
node tools/agents-judgment-calls-gate.js
node tools/agents-judgment-calls-gate.js --review --task "recommend whether to roll out the subsidy" --option-a "roll out" --option-b "discontinue" --choice A --prior A --lean B --case-a "local table clears the margin" --case-b "cost per yield stays under it" --reason "I keep roll out" --evidence "read coop-table.csv"
node tests/test-agents-judgment-calls-gate.jsThe status command does not call a model.
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.

