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 sainteye/clawdline --skill evidence-reviewgit clone --depth 1 https://github.com/sainteye/clawdlineWrote 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/sainteye/clawdline/evidence-review)<a href="https://agentmods.dev/skills/sainteye/clawdline/evidence-review"><img src="https://agentmods.dev/badge/skills/sainteye/clawdline/evidence-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/sainteye/clawdline/evidence-review"><img src="https://agentmods.dev/badge/skills/sainteye/clawdline/evidence-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 | $0.00036 | $0.00472 |
| Opus 5.5 | $0.00014 | $0.00189 |
| Sonnet 5.5 | $0.00007 | $0.00094 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
evidence-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 today.
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.
What it actually says
Evidence-led review
Review the actual revision and surrounding behavior. Existing project checks, acceptance rules and role skills remain authoritative. Keep review proportional to the change; this skill does not require another agent, an extra approval, or a full suite for every edit.
For a proposed change, make two separate judgments:
- Requested behavior: map each material requirement to the implementation and its evidence. Include negative and failure paths relevant to this change. Unavailable requirements remain unverified.
- Implementation quality: examine correctness, data ownership, concurrency, permissions, compatibility and maintainability where the diff touches them. A passing test does not establish all of these, and a preference is not a defect.
Report confirmed findings by severity with location, impact and supporting evidence. Distinguish pre-existing issues, optional improvements and unresolved questions. For a large change, inspect the integrated flow as well as individual tasks. Use an independent reviewer only when the task and project rules authorize it and the risk justifies it.
When receiving feedback, first restate the concrete proposed change and verify its premise against the current code, callers, supported platforms and documented decisions. Implement technically supported corrections; explain unsupported suggestions with evidence. Clarify only the part whose ambiguity blocks progress and continue independent authorized work.
Match acceptance evidence to its subject: a child success message needs its artifact and landing checked; deployment needs the intended version and served asset checked; a bug needs its original symptom retested. Report partial verification as partial. Do not modify or delete someone else's work while checking a claim.
Keep invocation evidence and findings in the normal Session history. If the current project has an approved workflow pilot, follow its own checkpoint and evidence limits. Do not launch extra model calls as part of ordinary review.
Adapted from obra/superpowers receiving-code-review and the spec/quality review distinction in subagent-driven-development at commit 2ce8aa15d05bd57213e6f746f953aafb7ded7a8b. Copyright (c) 2025 Jesse Vincent, MIT. No orchestration, model-selection or branch-finishing instructions were imported.
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.
- today First seen · 24 lines · 36 tokens per session scan A fd4c584fae5b
evidence-review is a skill published in the GitHub repository sainteye/clawdline (1 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 472 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 2026-10-30.
Other skills, from other repositories
swift-concurrency-pro
Reviews Swift code for concurrency correctness, modern API usage, and common async/await pitfalls. Use when reading, writing, or reviewing Swift concurrency code.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
gpui-mockup
Explore visual directions for a herdr-gpui UI element as real GPUI code. Write 3–4 variants in one Rust file, show them side by side in a native mockup window in the user's own theme and fonts, capture the window to check your work, and iterate on the picks and notes the user sends back. Use instead of the HTML mockup…
review-preflight
Review tooling for a PR: review-preflight prints REVIEW.md's criteria and the PR's live gate state before a review; ci-triage maps a PR's failing checks to already-filed issues.
code-refiner
Deep code simplification and refactoring preserving behavior across Python, Go, TypeScript, Rust. Targets complexity, anti-patterns, readability debt. Triggers on: "simplify this code", "refactor for clarity", "reduce complexity", "make this more readable", "tech debt cleanup", "too much nesting". NOT for deepening…
package-optimizer
Evaluate one existing package or bounded package family from recorded evaluator evidence and a capability profile, then propose retain, simplify, strengthen, retire, or inconclusive without editing. Use when optimizing a skill, agent, hook, rule, command, utility, or preset; evaluating whether package detail is…