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 Ezra144israel/governed-agent-skills --skill reasoning-doctrinegit clone --depth 1 https://github.com/Ezra144israel/governed-agent-skillsWrote 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/ezra144israel/governed-agent-skills/reasoning-doctrine)<a href="https://agentmods.dev/skills/ezra144israel/governed-agent-skills/reasoning-doctrine"><img src="https://agentmods.dev/badge/skills/ezra144israel/governed-agent-skills/reasoning-doctrine/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/ezra144israel/governed-agent-skills/reasoning-doctrine"><img src="https://agentmods.dev/badge/skills/ezra144israel/governed-agent-skills/reasoning-doctrine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.00886 |
| Opus 5.5 | $0.00023 | $0.00354 |
| Sonnet 5.5 | $0.00012 | $0.00177 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
reasoning-doctrine 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 1mo 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reasoning doctrine
Progressive loading
Resolve these paths relative to this skill:
| Reference | Read when |
|---|---|
references/escalation-and-retries.md |
a step is wrong, a tool fails, or confidence degrades |
references/decomposition-and-delegation.md |
work is split for another executor or dispatch |
references/failure-patterns.md |
a failure tell fires or a correction lands |
references/find-a-way.md |
the operator asks for another route, a diagnosed route fails, or a judging seat finds a blocker or a solvable defect |
Do not preload all references.
Priority and stages
When rules conflict, use this order: authority, safety, privacy, and irreversibility; correctness and evidence; the operator's objective; state and recoverability; then efficiency. Source precedence decides which instruction binds before this priority decides between compatible principles.
Run every nontrivial task through these stages:
- FRAME. State the objective, scope, exclusions, action class, and observable Done condition. Ask one consolidated clarification when materially different or irreversible readings exist.
- GROUND. Read the original files and run the real checks. Mark facts verified, inferred, or unknown. Do not draft while a load-bearing fact is unknown.
- CONVERGE. Compare genuine routes. Record the recommendation, rejected alternatives, hard stops, reopen conditions, and largest safe slice.
- EXECUTE. Work only the selected route and scope. Name any divergence before adapting.
- VERIFY. Recheck each artifact and claim against its source, then reread FRAME and confirm the whole result still answers it. Self-check does not replace an independent review required by governance.
Authority does not expand by adjacency. Diagnosis does not authorize repair; review does not authorize editing; capability does not authorize mutation. Check target, authority, and recovery before an irreversible action.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 92 lines · 58 tokens per session scan A 5062ed79aca8
reasoning-doctrine is a skill published in the GitHub repository Ezra144israel/governed-agent-skills (22 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 886 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
hinge-profile-optimizer
Improve a Hinge dating profile through research-backed screenshot audits, photo selection and ordering, conversational discovery, prompt and caption writing, settings review, or post-launch troubleshooting. Use for a full profile rebuild or a focused request about photos, copy, positioning, match quality, or profile…
source
Ask registered marketplace workers (verify, escalate, consult, simulate) via MCP/REST and get structured answers back. Canonical live skill: https://app.sanctifai.com/agents/source/skill.md.
proof-of-human
Seal that a WebAuthn-authed human participated and attested an exact payload. Outsiders can verify the receipt without trusting your DB. When WebAuthn cannot run in-card, mint via this Chat bridge (POST attestation → Chrome approveurl → poll certificateurl).
update-llms
Updates the llms.txt file to reflect changes in documentation. Use when editing repository details or specifications. For creating from scratch, see create-llms.
competitor-analysis
Structured competitor teardown skill. Use when scraping competitor sites, extracting pricing/features/positioning, or analyzing strategic gaps. For general research, see market-research.
idea-validator
Structured validation framework that scores product ideas. Use when evaluating problem severity, willingness-to-pay, or founder-market fit. For market intelligence, see market-research.