checklist-health

checklist-health is a skill for Claude Code from ArtemioPadilla/agent-triforce. It costs 42 tokens per session (1,308 once invoked), scanned A, original, MIT.

A workflow for measuring how well an organization's checklists work over time. It compares checklist items with past runs to find stale items and missing coverage.

In plain words
What is it for?
Use it to review checklists across the Prometeo, Forja, and Centinela agents, examine event history, and produce suggestions for improving them.
Why use it?
It helps reveal which checklist steps are rarely used, no longer relevant, or failing to cover important workflow risks.

Skill for Claude Code

Written for Claude Code: context: fork in frontmatter. Also seen: agent in frontmatter; reads .claude/ paths.

Good fit Use it to review checklists across the Prometeo, Forja, and Centinela agents, examine event history, and produce suggestions for improving them.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/artemiopadilla/agent-triforce/checklist-health
Install

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.

Any agent
npx skills add ArtemioPadilla/agent-triforce --skill checklist-health
Clone the repo
git clone --depth 1 https://github.com/ArtemioPadilla/agent-triforce

Made for: Claude Code.

Wrote 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.

agentmods badge for checklist-health

README.md
[![agentmods](https://agentmods.dev/badge/skills/artemiopadilla/agent-triforce/checklist-health/github.svg)](https://agentmods.dev/skills/artemiopadilla/agent-triforce/checklist-health)
Your own site
<a href="https://agentmods.dev/skills/artemiopadilla/agent-triforce/checklist-health"><img src="https://agentmods.dev/badge/skills/artemiopadilla/agent-triforce/checklist-health/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.

agentmods 80×15 button for checklist-health

Your own site · 80×15
<a href="https://agentmods.dev/skills/artemiopadilla/agent-triforce/checklist-health"><img src="https://agentmods.dev/badge/skills/artemiopadilla/agent-triforce/checklist-health.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,308 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.01308
Opus 5 $0.00021 $0.00654
Sonnet 5 $0.00008 $0.00262
Haiku 4.5 $0.00004 $0.00131

Measured 12d ago against content hash 01b0273295bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

checklist-health 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.

.claude/skills/checklist-health/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run a checklist health analysis across the Agent Triforce system.

Follow these steps:

SIGN IN:

  • Run the SIGN IN checklist from your agent file
  • Note any recent workflow runs or known checklist issues

READ CHECKLIST DEFINITIONS:

  1. Read all checklist definitions from the 3 agent files:
    • .claude/agents/prometeo-pm.md -- extract all checklist sections (SIGN IN, TIME OUT, SIGN OUT, NON-NORMAL)
    • .claude/agents/forja-dev.md -- extract all checklist sections
    • .claude/agents/centinela-qa.md -- extract all checklist sections
  2. For each checklist, record: agent name, checklist name, type (DO-CONFIRM or READ-DO), item count, and each item's text

READ EVENT HISTORY: 3. Read docs/checklist-health/events.jsonl if it exists

  • If the file does not exist, create docs/checklist-health/ directory and an empty events.jsonl file
  • Each line in events.jsonl follows this schema:
    {
      "checklist": "string (e.g., 'forja-dev/Implementation Complete')",
      "item_index": "number (0-based index within the checklist)",
      "item_text": "string (the checklist item text)",
      "workflow_run_id": "string (unique ID for the workflow run)",
      "timestamp": "string (ISO 8601 format)",
      "hit": "boolean (true if this item caught an issue)",
      "confirmed": "boolean (true if the caught issue was a real issue, not false positive)",
      "issue_type": "string (optional, category of the issue caught)"
    }
    
  1. If fewer than 10 workflow runs are recorded, note this in the report as insufficient data for statistical analysis but proceed with available data

ANALYZE: 5. Calculate hit rate per checklist item:

  • Hit rate = (events where hit=true AND confirmed=true) / (total events for that item)
  • Group by checklist, then by item
  1. Identify stale items: items with 0 confirmed hits in the last 20 workflow runs
    • These are candidates for removal or rewording
    • Check if the item is a safety-critical "last resort" item (e.g., security checks) -- these should not be removed even with 0 hits
  2. Identify coverage gaps:
    • Look at issue types from events where hit=false but an issue was found later (post-checklist discovery)
    • Look at recurring issue types in docs/reviews/ that do not map to any existing checklist item
    • Cross-reference with TECH_DEBT.md for patterns of recurring debt
  3. Generate suggested new checklist items for identified gaps:
    • Follow Boorman's principles: simple, verifiable, under 10 words
    • Assign to the most appropriate agent and checklist
    • Mark as "Suggested" -- never auto-add to checklists

TIME OUT -- Analysis Verification (DO-CONFIRM):

  • All 3 agent files read and all checklists extracted
  • Event history parsed without errors (or empty state handled)
  • Hit rates calculated correctly (denominator is opportunities, not total events)
  • Stale items identified with context (safety-critical items flagged separately)
  • Coverage gaps cross-referenced with reviews and tech debt
  • Suggested items follow Boorman's principles (simple, verifiable, <10 words)

GENERATE REPORT: 9. Write the report to docs/checklist-health/report-{date}.md using this structure:

# Checklist Health Report -- {YYYY-MM-DD}

## Summary
- Total checklists analyzed: {N}
- Total checklist items: {N}
- Workflow runs in dataset: {N}
- Data sufficiency: {Sufficient (>=10 runs) | Insufficient (<10 runs)}

## Hit Rates by Checklist

### {Agent Name} -- {Checklist Name} ({Type})
| # | Item | Hits | Opportunities | Hit Rate | Status |
|---|------|------|---------------|----------|--------|
| 1 | {item text} | {N} | {N} | {N%} | Active / Stale / Safety-Critical |

## Stale Items (Candidates for Review)
Items with 0 confirmed hits in the last 20 runs:
- [{agent}/{checklist}] Item {N}: "{text}" -- Consider: removal | rewording | reclassify as safety-critical

## Coverage Gaps
Issue types found in reviews/workflow but not covered by any checklist item:
- **{issue type}**: Found {N} times. No corresponding checklist item exists.

## Suggested New Items
| Agent | Checklist | Suggested Item | Rationale |
|-------|-----------|---------------|-----------|
| {agent} | {checklist} | {<10 word item} | {why this item is needed} |

## Recommendations
{Prioritized list of actions: items to remove, items to reword, items to add}

Read the full file on GitHub · 116 lines

Changes

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.

  1. 12d ago First seen · 116 lines · 42 tokens per session scan A 01b0273295bc

Subscribe to this mod's changes

checklist-health is a skill published in the GitHub repository ArtemioPadilla/agent-triforce (3 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 1,308 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

fellowship

Multi-task orchestrator. Coordinates agent teammates (led by Gandalf) running /quest (code) or /scout (research) workflows. Use when you have multiple independent tasks to run in parallel.

justinjdev/fellowship · 45 tokens

quest

Use for multi-file or multi-step changes that need research and a plan — not single-file fixes under 50 lines that follow an existing pattern (see Escape Hatch below). Runs the Research → Plan → Implement → Review lifecycle with a hard gate leaving each of the first three phases and context compaction between them.

justinjdev/fellowship · 64 tokens

retro

Invoke after a fellowship disbands, or when the user explicitly asks for a retrospective. Collects gate history, palantir alerts, and quest metrics to surface patterns and interactively recommend configuration improvements.

justinjdev/fellowship · 42 tokens

council

Invoke when the user runs /council or from /scout. Quest inlines this orientation as its Research step 2 and does not call it. Loads focused, task-relevant context by reading CLAUDE.md, scanning for related files, and producing a structured Session Context block.

justinjdev/fellowship · 63 tokens

lembas

Use between workflow phases or when context feels bloated. Writes a structured checkpoint capturing task, findings, files, state, and next steps, then continues from that summary instead of the full history. Invoke standalone or automatically between quest phases.

justinjdev/fellowship · 51 tokens

missive

Invoke only when spawning a quest from a GitHub issue reference. Fetches GitHub issue context for quest spawning. Parses issue references, retrieves structured data via gh, and produces branch suggestions and PR keywords. Used standalone or as input to quest orchestration.

justinjdev/fellowship · 54 tokens