Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add chrbailey/promptspeak-mcp-server --skill hold-triagegit clone --depth 1 https://github.com/chrbailey/promptspeak-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chrbailey/promptspeak-mcp-server/hold-triage)<a href="https://agentmods.dev/skills/chrbailey/promptspeak-mcp-server/hold-triage"><img src="https://agentmods.dev/badge/skills/chrbailey/promptspeak-mcp-server/hold-triage/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chrbailey/promptspeak-mcp-server/hold-triage"><img src="https://agentmods.dev/badge/skills/chrbailey/promptspeak-mcp-server/hold-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00029 | $0.00371 |
| Opus 5 | $0.00015 | $0.00186 |
| Sonnet 5 | $0.00006 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
hold-triage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
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.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 42 lines · 29 tokens per session scan A a5a5ef539487
hold-triage is a skill published in the GitHub repository chrbailey/promptspeak-mcp-server (1 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 371 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
patsnap-patent-literature-search
Search Patsnap's global patent and scientific literature databases together using natural-language, semantic, keyword, and BM25-based queries with multidimensional filters, then fetch patent or literature records as Markdown.
complyedge-eu-ai-act-runtime-deny
Runtime deny for EU AI Act Article 5 and Article 50 on this prompt or output via ComplyEdge TrustLint MCP. Use when the user wants agent I/O compliance enforcement, not system classification, FRIA forms, or C2PA watermarking.
event-staffing-procurement
Answer event staffing procurement and vendor-onboarding questions, then bridge a real event into a staffing plan. Use when a buyer, procurement team, or venue asks about certificates of insurance (COI), W-9 or tax documentation, liability and workers' compensation coverage, cancellation and payment terms, invoicing…
event-staffing-compliance
Assess worker-classification and compliance risk for temporary event staffing in the US and Canada. Use when a user asks about W-2 vs 1099 event workers, misclassification penalties, joint-employer liability, certificates of insurance (COI), wage/hour rules for event staff, or whether a staffing arrangement is…
memory-search-mcp
Long-term memory and context retrieval for AI agents. Semantic search across conversation history with care-weighted relevance.
web-research-mcp
Intelligent web research with source validation. Automated research synthesis with citation tracking and fact verification.