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 maxkle1nz/m1nd --skill m1nd-guardiangit clone --depth 1 https://github.com/maxkle1nz/m1ndWrote 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/maxkle1nz/m1nd/m1nd-guardian)<a href="https://agentmods.dev/skills/maxkle1nz/m1nd/m1nd-guardian"><img src="https://agentmods.dev/badge/skills/maxkle1nz/m1nd/m1nd-guardian/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/maxkle1nz/m1nd/m1nd-guardian"><img src="https://agentmods.dev/badge/skills/maxkle1nz/m1nd/m1nd-guardian.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 | $0.00099 | $0.01622 |
| Opus 5 | $0.00049 | $0.00811 |
| Sonnet 5 | $0.00020 | $0.00324 |
| Haiku 4.5 | $0.00010 | $0.00162 |
Grade A, and why
m1nd-guardian 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 11d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
m1nd-guardian
This skill turns M1ND-10 continuation into a proof-carrying, resumable process. It complements
m1nd-operator; it does not replace repository law, frozen contracts, the current handoff, direct
proof, or owner authority.
Required reading
Before changing M1ND-10 implementation, read completely and in order:
- repository
AGENTS.md; docs/M1ND-10-PRD.md;docs/M1ND-10-UML.md;- the owner-ratification receipt named by the current handoff;
- the newest
docs/M1ND-10-HANDOFF-*.md; docs/PATHOS.md;docs/M1ND-GUARDIAN-METHOD.md;- the proof artifact for the active front.
The current handoff wins over stale counts, old reviews, previous tasks, and this skill's examples. Frozen PRD/UML files are not edited in place.
First safe move
- Resolve the checkout with
git rev-parse --show-toplevel. - Record revision,
git status --short, frozen-contract hashes, and protected runtime boundaries. - Use
m1nd-operatorfor orientation only when reception covers the checkout. - If the handoff forbids the served owner, do not contact it. Use an isolated CLI orientation.
- If isolated orientation returns
needs_authorityor no governed ingest provider, do not invent authority. Switch to direct source, test, compiler, log, and focused-probe truth. - Name One active front, its acceptance checks, proof level, and stop conditions.
Guardian loop
ORIENT -> PROTECT -> CUT -> PROVE -> CONFRONT -> RATIFY -> LAND -> REMEMBER
- ORIENT: establish checkout, binding, current blocker, authority, and honest gaps.
- PROTECT: preserve unrelated dirty work; never reset, clean, stash, overwrite, install, or delete for convenience.
- CUT: work on one proof boundary. Do not open downstream gates early.
- PROVE: focused adversarial tests, affected aggregates, hygiene checks, hashes, then required isolated live/platform proof.
- CONFRONT: send a bounded read-only packet to an independent reviewer at load-bearing seams.
CHANGEblocks promotion; no verdict isNOT_PROVEN. - RATIFY: agents propose and verify. Human-only authority ratifies, lands, publishes, installs, activates, and closes G10 where the contract requires it.
- LAND: compose receipts only when they bind to the same immutable candidate and candidate digest.
- REMEMBER: update proof, handoff, PATHOS, affected docs, exact next move, and non-claims.
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.
- 11d ago First seen · 150 lines · 99 tokens per session scan A 9c97869cb8f6
m1nd-guardian is a skill published in the GitHub repository maxkle1nz/m1nd (22 stars, last pushed 3d ago), licensed MIT. It adds 99 tokens to every session and 1,622 once invoked, about $0.0005 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
trace-mcp
Use trace-mcp tools for code navigation, impact analysis, and framework-aware queries instead of Read/Grep/Glob/Bash. Activate whenever the agent needs to explore, understand, or modify a codebase that has trace-mcp indexed.
trace-mcp-codemod
Use trace-mcp applycodemod for any bulk mechanical change instead of repeated Edit calls. Activate whenever the same edit pattern would be applied 2+ times, across one file or many.
trace-mcp-pre-commit
Run trace-mcp security, quality-gate, and antipattern checks before committing or opening a PR. Activate when the agent is about to create a commit or pull request in a project indexed by trace-mcp.
trace-mcp-refactoring
Safe refactoring workflow using trace-mcp — assess risk, find candidates, check impact, and rename symbols across all files without missing import sites or cross-file references.
qartez
Semantic code intelligence skill for qartez MCP. Use qartez tools for code exploration, impact analysis, and guarded refactors; treat built-in code-tool denials as routing signals and recover via qartez replacements.
research
Performs deep research on a topic via deepresearch. Simulates a multi-step research process and returns a comprehensive research result as a string.