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 45ck/skill-harness --skill evidence-gap-reviewgit clone --depth 1 https://github.com/45ck/skill-harnessWrote 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/45ck/skill-harness/evidence-gap-review)<a href="https://agentmods.dev/skills/45ck/skill-harness/evidence-gap-review"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/evidence-gap-review/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/45ck/skill-harness/evidence-gap-review"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/evidence-gap-review.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 | $0.00024 | $0.00700 |
| Opus 5 | $0.00012 | $0.00350 |
| Sonnet 5 | $0.00005 | $0.00140 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
evidence-gap-review 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 6d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review the output of specgraph verify (or specgraph verify --json) and produce an actionable gap report.
Procedure
- Run
specgraph verify(or read the provided output). - For each spec with status
WARN,FAIL, orINSUFFICIENT:- Identify the required evidence dimension(s) that are unmet.
- State the current evidence level and what level is needed.
- Suggest the lowest-effort action that would provide the required evidence.
- Group findings by effort: low (annotation), medium (test), high (architecture decision).
Evidence-gap action map
| Required level | Unmet because | Recommended action |
|---|---|---|
| E0 | No @spec annotation |
Add /** @spec ID @implements Feature */ to the implementation file |
| E1 | No closed Beads issue or structural artifact | Create a Beads issue with --spec-id ID and close it when done |
| E2 | Not indexed in specgraph DB / no linked artifact | Run specgraph verify to store claims, add cross-refs via depends_on |
| E3 | No test annotation | Add /** @spec ID @verifies Feature */ to a test file |
| E4 | No CI artifact | Configure freshness.artifacts in .specgraph/config.json |
Status meanings
| Status | Meaning |
|---|---|
PASS |
All required evidence thresholds met |
WARN |
Evidence exists but below required strength for this state |
FAIL |
No evidence found for a required dimension |
INSUFFICIENT |
Evidence found but strength is below required level (e.g. E0 found, E2 required) |
SKIP |
Spec has no evidence requirements (draft/deprecated) |
WAIVED |
Requirement waived — check expiry |
Output format
For each gap, output:
SPEC-ID [WARN|FAIL|INSUFFICIENT] dimension=<name> need=<Ex> have=<Ey|none>
→ Action: <one-line description>
Then a prioritised action list (most impactful first).
Useful drill-down commands
specgraph verify # summary table for all specs
specgraph verify --json # machine-readable output
specgraph verify --spec SPEC-ID # single spec only
specgraph explain SPEC-ID # full claim breakdown for one spec
specgraph find --spec SPEC-ID # locate files that reference a spec
specgraph find --relation IMPLEMENTS # all IMPLEMENTS claims
specgraph find --strength 1 # E1 and above
specgraph waivers # list active waivers
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.
- 6d ago First seen · 69 lines · 24 tokens per session scan A 138fdb45b8a7
evidence-gap-review is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 700 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
do-it-verify
Use when selecting evidence for a delivery claim, regression fix, installation, or branch closeout.
typescript-sdk
Implement or modify TypeScript SDK behavior in @composio/core or shared TypeScript packages, including tools, toolkits, sessions, auth configs, connected accounts, modifiers, and generated SDK surfaces. Use for TS runtime/API work; pair with typescript-testing for verification and cross-sdk-parity when Python must…
bug-fixing
Fix defects in the Composio SDK repository with focused reproduction, root-cause analysis, regression tests, and narrow verification. Use when the user reports a bug, failing test, CI regression, runtime defect, or incorrect SDK behavior. Do not use for new feature design or broad refactors.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
python-providers
Create, modify, test, or package Python provider adapters under python/providers, including framework-specific dependencies, public imports, type inference, and provider metadata. Use for Python provider work only; use python-sdk for core SDK changes.
python-sdk
Implement or modify Python SDK behavior under python/composio, including tools, toolkits, sessions, auth configs, connected accounts, client integration, and shared Python models. Use for Python core runtime/API work; pair with python-testing and cross-sdk-parity when TypeScript must match.