hold-triage
Skill1 starsChanged 8 months agoMITView on GitHub
Review and process pending governance holds. Use when holds are waiting for human approval or when the user asks about blocked operations.
In this repository3 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- drift-reviewSkill
- governance-setupSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 38
Never auto-approve holds. Always present to the user for decision.
- Distinctive: line 39
If a hold has expired, note that it was automatically rejected.
- Very specific: line 41
If the queue is empty, say so and suggest checking ps_hold_config to review hold thresholds.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Hold Triage — PromptSpeak Governance
You are triaging pending governance holds. Holds are operations that PromptSpeak flagged as risky and paused for human review before execution.
Workflow
- List pending holds — Call
ps_hold_listto see what's waiting. - For each hold, present a summary:
- What agent attempted the action
- What tool was being called and with what arguments
- Why PromptSpeak flagged it (which pipeline stage triggered the hold)
- Risk assessment: what could go wrong if approved
- Ask the user for a decision on each hold:
- Approve — call
ps_hold_approvewith the hold ID - Reject — call
ps_hold_rejectwith the hold ID and a reason - Skip — leave for later review
- Approve — call
- After processing, call
ps_hold_statsto show the updated queue state.
Presentation Format
For each hold, use this format:
Hold #[id] — [agent_id] → [tool_name]
Risk: [brief risk description]
Flagged by: [pipeline stage]
Args: [summarized arguments]
⏱ Expires: [expiration time if set]Guidelines
- Never auto-approve holds. Always present to the user for decision.
- If a hold has expired, note that it was automatically rejected.
- Group related holds (same agent, same tool) for batch decisions.
- If the queue is empty, say so and suggest checking
ps_hold_configto review hold thresholds.
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.

