Borrowing it
Nothing to install: this file belongs to daniloc/mnemion. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/daniloc/mnemion/main/.claude/skills/mnemion-doctrine/SKILL.mdgit clone --depth 1 https://github.com/daniloc/mnemionWrote 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/daniloc/mnemion/mnemion-doctrine)<a href="https://agentmods.dev/skills/daniloc/mnemion/mnemion-doctrine"><img src="https://agentmods.dev/badge/skills/daniloc/mnemion/mnemion-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/daniloc/mnemion/mnemion-doctrine"><img src="https://agentmods.dev/badge/skills/daniloc/mnemion/mnemion-doctrine.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 | $0.00124 | $0.02581 |
| Opus 5 | $0.00062 | $0.01290 |
| Sonnet 5 | $0.00025 | $0.00516 |
| Haiku 4.5 | $0.00012 | $0.00258 |
Grade A, and why
mnemion-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 10d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This is the doctrine the Mnemion codebase converged on. It is not style advice — it is the reason the security surface stopped leaking and the structure stays coherent under agentic editing. Apply it; do not relitigate it. Full derivation (the why, the retrospective, the physics) is in references/doctrine.md.
The one rule
A recurring bug is a structural question being answered at call sites instead of at a boundary. Don't patch faster — invert the architecture so the bug becomes unrepresentable.
The fix-one-open-another loop is the diagnosis. When you see two or more findings clustered on the same seam, stop patching instances and enforce the invariant from a single home.
The core conversion: O(N) → O(1)
Turn a block-list (N guards you must remember at N sinks; fails open the moment one is forgotten) into a chokepoint (one reference monitor every path physically crosses). A chokepoint earns trust from four properties that travel together — miss one and drift returns:
- One declarative home, and it's data. A table keyed by the thing it governs. Not a predicate copied across call sites. Not a naming convention standing in for an unmodeled fact (
startsWith("_")was kernel-ness inferred from a string — a bug). Not prose in a doc. - Derive, never duplicate. Every gate computes from the table. This is
data-is-destinyapplied to behavior: store the rule once, derive its enforcement. - Enforce at the chokepoint the invariant is about — where all paths converge on the protected thing, not the convenient layer. (The ingress consent-bypass happened because consent lived in the session layer while the invariant was about the write.)
- Fail closed. Absence resolves to the safe state. Unclassified → denied, not open. Forgetting to update the table must be safe.
The linchpin: prove totality
A chokepoint is not enough — you must know it's the only path. A totality oracle converts the unanswerable block-list question ("did we find every sink?") into a checkable one ("does the one declaration cover the enumerable domain, and fail loud if not?").
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.
- 10d ago First seen · 99 lines · 124 tokens per session scan A 0dc66588ff3d
mnemion-doctrine is a skill published in the GitHub repository daniloc/mnemion (22 stars, last pushed 20d ago), licensed MIT. It adds 124 tokens to every session and 2,581 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…