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 allemaar/open-skills --skill map-checkgit clone --depth 1 https://github.com/allemaar/open-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/allemaar/open-skills/map-check)<a href="https://agentmods.dev/skills/allemaar/open-skills/map-check"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/map-check/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/allemaar/open-skills/map-check"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/map-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low Excessive Agency · line 17 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00093 | $0.01779 |
| Opus 5 | $0.00046 | $0.00890 |
| Sonnet 5 | $0.00019 | $0.00356 |
| Haiku 4.5 | $0.00009 | $0.00178 |
Grade A, and why
map-check 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 9d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/map-check
The read-only conformance front door for Map Your Knowledge (MYK) — the single checking engine. It validates a scope against the frozen contract's deterministic catalog and never invents rules of its own.
kernel-version: MYK v2.3
f2f96f2de49b4863bca55ee8f6004d24e00574a7db5e7e5ef0e3cb28c42510cf
The two iron rules
- Read-only forever. map-check never writes, renames, or proposes-and-applies. Findings go to the Handler, and repairs run through
map-this(one-off) ormap-maintain(the tending loop). - Unqualified CLEAN is banned. The only positive verdict is: "clean for checks {list} over inventory {source}, mode {mode}; not checked: {list}." A crash can never read as a pass: the JSON envelope separates operational errors from findings by shape.
Running it
The bundled deterministic script does the mechanical work (no LLM in the validation path):
node <this-skill>/references/tools/map-check.mjs <target-path> [--json]
- Target classes: an explicit path inside a scope, or a scope root (a directory containing
.myk/README.mdor a declared root map). Ambiguous or contested scopes fail closed (scope-conflict). - Modes: FULL (a
.myk/README.mdcontract is present — itsm1.root-mapandm3declarations govern) or DEGRADED (no contract — the agent supplies the declared root map from kernel markers; absence of any declaration is NEVER a finding: undeclared trees are outside jurisdiction, and the script says so and stops). - Inventory honesty: the script walks the scope itself (never following links/junctions out of it; skipped boundaries are counted against completeness) and reports
inventory: {source, complete, scanned}. - Exit codes:
0ran, zero findings (qualified-clean) ·1ran, findings present ·2operational error ·3target/scope resolution error.
The checks (each pinned to its kernel rule; the script prints this table per run)
| Id | Checks | Finding classes |
|---|---|---|
| C1 owner-declaration | every eligible Markdown member declares exactly one meta.map; the declared root map declares none |
missing-owner · multiple-owners · root-declares-owner |
| C2 reciprocal spine | roster derived from member-side meta.map (authoritative): each declared owner map exists AND links the member; untyped map links are never membership claims |
spine-drift-mapside · dangling-owner |
| C3 address form | duplicate-basename targets (incl. any README owner) use path form, never bare |
bare-duplicate-basename |
| C4 meta container | frontmatter parses; single well-formed meta; one meta.map value; the exact legacy key meta.parent |
parse-error · malformed-map-value · legacy-owner-key |
| C5 archive consistency | meta.archived implies the archive callout; archive/ folders reported as likely-unsignalled |
missing-callout · unsignalled-archive |
| C7 case-fold collisions | sibling names colliding case-insensitively | case-fold-collision |
| C8 exclusion integrity | M3 entries well-formed; excluded trees generate zero other findings; managed artifacts reachable per their declared graph-entry | malformed-exclusion · managed-artifact-unreachable |
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.
- 9d ago First seen · 74 lines · 93 tokens per session scan A e77dc1201db4
map-check is a skill published in the GitHub repository allemaar/open-skills (14 stars, last pushed 23d ago), licensed Apache-2.0. It adds 93 tokens to every session and 1,779 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
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
cli-eval
Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.
model-merging
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.