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 paruff/uFawkesAI --skill ai-policy-lifecyclegit clone --depth 1 https://github.com/paruff/uFawkesAIWrote 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/paruff/ufawkesai/ai-policy-lifecycle)<a href="https://agentmods.dev/skills/paruff/ufawkesai/ai-policy-lifecycle"><img src="https://agentmods.dev/badge/skills/paruff/ufawkesai/ai-policy-lifecycle/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/paruff/ufawkesai/ai-policy-lifecycle"><img src="https://agentmods.dev/badge/skills/paruff/ufawkesai/ai-policy-lifecycle.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 | $0.00054 | $0.01601 |
| Opus 5 | $0.00027 | $0.00800 |
| Sonnet 5 | $0.00011 | $0.00320 |
| Haiku 4.5 | $0.00005 | $0.00160 |
Grade A, and why
ai-policy-lifecycle 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.
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: AI Policy Lifecycle
Load trigger:
"load ai-policy-lifecycle skill"> DORA: AI Capability 1 (Clear and communicated AI stance) Token cost: Low
Purpose
ai-stance creates AI_STANCE.md. This skill keeps it alive.
A static AI policy document becomes a liability within one tool adoption cycle. The DORA AI Capabilities Model v2025.1 explicitly warns against treating AI policy as a one-time artifact. This skill defines the quarterly review cadence, the process for updating the three buckets when circumstances change, and the socialization pattern that ensures every contributor (human and agent) encounters the updated policy.
Review Triggers
| Trigger | Action | Priority |
|---|---|---|
| Quarterly calendar (every 90 days) | Full review — run all five steps | Medium |
| New AI tool adopted | Update Permitted tools table + re-assess Prohibited/Guardrails | High |
| Security incident involving AI tool | Immediate review of relevant bucket | Critical |
| New contributor onboarded | Verify they've read AI_STANCE.md | Low |
| DORA AI Capabilities research updated | Check if new capability changes the stance framing | Low |
GitHub issue labeled ai-policy filed |
Triage and incorporate if valid | Medium |
Five-Step Review Process
Step 1 — Freshness check (5 min)
# Check last review date
grep "Last reviewed:" AI_STANCE.md
# Check days elapsed
python3 -c "
from datetime import datetime
last = datetime.strptime('YYYY-MM-DD', '%Y-%m-%d')
print(f'{(datetime.utcnow() - last).days} days since last review')
"
# Check for open ai-policy issues
gh issue list --repo paruff/REPO_NAME --label "ai-policy" --state open
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 · 170 lines · 54 tokens per session scan A 5247cada6885
ai-policy-lifecycle is a skill published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed 20d ago), licensed MIT. It adds 54 tokens to every session and 1,601 once invoked, about $0.0003 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
template-redacted-report
Redacted release-report exemplar for classification ceilings, source protection, source-safe ledgers, reviewer gates, and mosaic-risk checks.
aviation-inspector
Use when a task needs the judgment of an Aviation Inspector — determining whether an air carrier's fleet is in compliance with an Airworthiness Directive across a maintenance-records sample, deciding where the FAA's compliance-and-enforcement ladder places a finding (compliance action vs. Letter of Correction vs.…
avionics-technician
Use when a task needs the judgment of an avionics technician — chasing an intermittent nav/comm or autopilot fault that "checks good" on the ground, deciding whether an avionics upgrade needs an STC or qualifies for field approval, verifying bonding resistance and wire-bundle separation on an install, cross-checking a…
bailiff
Use when a task needs the judgment of a bailiff or court officer — deciding whether an in-custody defendant appears in visible or concealed restraints, running courtroom entry screening and staffing it for expected volume, handling a disruptive defendant or spectator under the judge's authority, moving a jury note…
blaster
Use when a task needs the judgment of a licensed blaster-in-charge — designing a bench or trench blast pattern, checking a shot against vibration/flyrock regulatory limits, sequencing detonator delays, handling a misfire, or reviewing explosives magazine storage and transport compliance.
boilermaker
Use when a task needs the judgment of a Boilermaker — qualifying or selecting a welding procedure for a pressure-boundary repair, deciding whether a defect is a code "repair" or an "alteration" under the National Board Inspection Code, sizing a tube-to-drum rolled joint expansion, reading radiographic or ultrasonic…