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 AndreiBozantan/svelte-axum-template --skill triage-review-findinggit clone --depth 1 https://github.com/AndreiBozantan/svelte-axum-templateWrote 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/andreibozantan/svelte-axum-template/triage-review-finding)<a href="https://agentmods.dev/skills/andreibozantan/svelte-axum-template/triage-review-finding"><img src="https://agentmods.dev/badge/skills/andreibozantan/svelte-axum-template/triage-review-finding/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/andreibozantan/svelte-axum-template/triage-review-finding"><img src="https://agentmods.dev/badge/skills/andreibozantan/svelte-axum-template/triage-review-finding.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 | $0.00059 | $0.00577 |
| Opus 5 | $0.00030 | $0.00289 |
| Sonnet 5 | $0.00012 | $0.00115 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
triage-review-finding 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage a Code Review Finding
The user pastes a finding produced by a reviewer (often another AI model of varying quality). The job is to independently verify it before any code changes — findings may be outdated, overstated, wrong about the code, correct but with a bad suggested fix or have a bad problem-solution fit.
Process
-
Read the actual code first. Locate the code the finding refers to (paths in the finding may be stale after refactoring — search by symbol name if the path doesn't exist). Understand the full flow, not just the quoted lines.
-
Verify each claim independently. Check the factual claims against the code as it is now. The finding may already be fixed, may misread the logic, or may describe a code path that cannot be reached. For claims about library behavior or security best practices, verify against documentation or a web search when falsifiable.
-
Judge severity honestly. Classify as: valid and important / valid but minor / partially valid (explain which parts) / invalid or outdated. An issue that is theoretically real but unreachable or irrelevant for this app's threat model should be labeled as such.
-
Evaluate the suggested fix separately from the finding. A real problem can come with a wrong or over-engineered fix. Propose the simplest fix that matches project conventions (see AGENTS.md), and mention meaningful alternatives with a recommendation.
-
Explain, then stop. Present the assessment: what the finding claims, what the code actually does, verdict, and proposed fix. Do NOT change code until the user agrees — unless they already said "fix it if it makes sense" in the same message. Plan the changes as a set of small commits.
-
When implementing: After the plan is approved, the commits should be done one-by-one, with user review. Add or extend tests that would have caught the issue (for race conditions, prefer a deterministic failing test before the fix). Run the relevant checks. Do not commit the changes.
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 · 33 lines · 59 tokens per session scan A 3412c04a02ed
triage-review-finding is a skill published in the GitHub repository AndreiBozantan/svelte-axum-template (2 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 577 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
privacy-first
Prevent email addresses and personal data from entering the codebase. Use when user asks to "prevent emails", "remove personal data", "privacy check", "no email", or when writing/editing any Rust code, Cargo.toml, config, or documentation files. Also triggers during code review, quality gate checks, or when adding…
skill-evaluator
Reusable skill for evaluating other skills with structure checks, eval coverage review, and real usage spot checks. Use when you need to check a skill, add evals, benchmark a skill, validate outputs against assertions, or compare current skill behavior against a baseline.
lint-rust
Run comprehensive linting and static analysis on Rust code including clippy, format check, security audit, supply chain, and unused dependencies. Use before committing, during CI, or when reviewing code quality. Triggers: "lint rust", "clippy", "static analysis", "code quality".
secret-lint
Automated secret scanning using secretlint to prevent credential leaks.
anti-ai-slop
Apply this skill when auditing, writing, or reviewing Rust code to avoid generic "AI slop" patterns: boilerplate structs with no purpose, copy-paste error handling, meaningless variable names, over-engineered abstractions, or hollow documentation. Triggers: "this looks AI-generated", "too much boilerplate"…
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.