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 jstoup111/ai-conductor --skill coverage-bindinggit clone --depth 1 https://github.com/jstoup111/ai-conductorWrote 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/jstoup111/ai-conductor/coverage-binding)<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/coverage-binding"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/coverage-binding/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/jstoup111/ai-conductor/coverage-binding"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/coverage-binding.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 | $0.00015 | $0.00941 |
| Opus 5.5 | $0.00006 | $0.00376 |
| Sonnet 5.5 | $0.00003 | $0.00188 |
| Haiku 4.5 | $0.00002 | $0.00094 |
Grade A, and why
coverage-binding 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 24d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Judgement policy
Each claim is judged independently against its cited task's Done when checks. For each claim,
answer this one question: does at least one cited check assert that claim's criterion? No claim's
verdict may be inferred from another claim.
Return asserts only when a cited check explicitly requires the criterion's behavior. Topical
adjacency, related implementation work, or a plausible inference is does-not-assert when the
check does not actually require that behavior.
Judge observable outcomes, not wording. A check that requires the same observable outcome with equal or greater precision asserts it, even when phrased differently: "rejected naming the field" asserts "the rejection names the field", and "byte-identical" asserts "equal". A check with lesser precision does not: "deep-equal" does not assert "byte-identical". A criterion clause that only restates the consequence of an asserted check's failure under an existing gate (for example "fails before the change can land" when the check asserts the integrity suite fails) is asserted by that check. Every other outcome in the criterion, including absence and no-op outcomes, still needs a check that requires it.
A check asserts every outcome its required observable state entails. A check that pins an exact
final state asserts the absence of any other change to that state: "the inbox listing equals the
seeded listing minus the claimed file" asserts "no other inbox file is renamed", and "ledger.json
is byte-identical before and after" asserts "no entry's status, attempts, or timestamps change".
Judge entailment from the supplied text alone; do not assume implementation behavior.
Judge only the supplied criterion's own clauses. Never require an outcome the criterion does not
state, and never require a check to restate a criterion word whose observable outcome the check
already pins. Before returning does-not-assert, name in missingAssertion the exact criterion
clause no cited check requires, quoted from the criterion; if you cannot quote one, the verdict is
asserts.
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.
- 24d ago Changed · +14 lines 254a8eda6b29
- 26d ago Changed · +12 lines 037b672c4d13
- 1mo ago Changed 61a257cb29f5
- 1mo ago Changed · +9 lines d348b1a7cb19
- 1mo ago Changed · +10 lines b0cd02d5a39d
- 1mo ago Changed · -5 lines 52a6bd189242
- 1mo ago First seen · 36 lines · 15 tokens per session scan A 73dfc7090975
coverage-binding is a skill published in the GitHub repository jstoup111/ai-conductor (7 stars, last pushed yesterday), licensed Apache-2.0. It adds 15 tokens to every session and 941 once invoked, about $0.0001 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 2026-09-06.
Other skills, from other repositories
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.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.