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 0ryant/engineering-doctrine --skill evidence-graded-citationgit clone --depth 1 https://github.com/0ryant/engineering-doctrineWrote 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/0ryant/engineering-doctrine/evidence-graded-citation)<a href="https://agentmods.dev/skills/0ryant/engineering-doctrine/evidence-graded-citation"><img src="https://agentmods.dev/badge/skills/0ryant/engineering-doctrine/evidence-graded-citation/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/0ryant/engineering-doctrine/evidence-graded-citation"><img src="https://agentmods.dev/badge/skills/0ryant/engineering-doctrine/evidence-graded-citation.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 | $0.00080 | $0.01007 |
| Opus 5.5 | $0.00032 | $0.00403 |
| Sonnet 5.5 | $0.00016 | $0.00201 |
| Haiku 4.5 | $0.00008 | $0.00101 |
Grade A, and why
evidence-graded-citation 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence-Graded Citation Skill
Kind: always-on primer for any evidence-bearing output Authority: advisory; grades are the author's claim and are reviewable
Purpose
Make the two-axis scheme of source-authority-and-evidence-grading.md mechanical at the point of writing: every citation says what kind of source it is, every claim says how well it is supported, and the admission floors for normative strength are applied before a MUST is written rather than discovered at review.
Instructions
When you cite a source to support a claim:
1. Tag every citation with its source-authority class S1 to S7 or X, record the accessed date, and pin the revision where the source is versioned.
2. Grade the claim, not the citation. C1 needs two independent S1-S4 sources with no credible contrary source; C2 needs one S1-S4 source or two independent S5-S6 sources; C3 is a single S5-S6 source or practitioner consensus; C4 is conflicting evidence or X-only support. Independent means different organisations with different incentives.
3. A MUST needs C1, or C2 with a stated risk asymmetry, or a registered entry in doctrine/EVIDENCE-EXCEPTIONS.md. A SHOULD needs C2, and single-source support must be flagged at the claim. X supports no normative claim.
4. Conformance claims are satisfied by the pinned norm itself; do not demand a second copy of a standard. Empirical claims about people and organisations cap at C2 on practitioner sources alone.
5. Look for disconfirming sources before grading. "No contrary evidence found after looking" is a statement you must be able to defend by saying where you looked.
6. Write the grade beside the claim as [S<n> C<n>, accessed YYYY-MM-DD]. A citation you cannot classify is X.
Run-Contract Use
context:
skills:
- [email protected]
verifiers:
- [email protected]
What ships with it
1 file 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 Changed · +1 lines aa918d7a6c2c
- 1mo ago First seen · 89 lines · 80 tokens per session scan A 582a81340e5d
evidence-graded-citation is a skill published in the GitHub repository 0ryant/engineering-doctrine (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 80 tokens to every session and 1,007 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…