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 fix-issuegit 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/fix-issue)<a href="https://agentmods.dev/skills/andreibozantan/svelte-axum-template/fix-issue"><img src="https://agentmods.dev/badge/skills/andreibozantan/svelte-axum-template/fix-issue/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/fix-issue"><img src="https://agentmods.dev/badge/skills/andreibozantan/svelte-axum-template/fix-issue.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 | $0.00065 | $0.01111 |
| Opus 5 | $0.00032 | $0.00556 |
| Sonnet 5 | $0.00013 | $0.00222 |
| Haiku 4.5 | $0.00006 | $0.00111 |
Grade A, and why
fix-issue 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 10d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix a GitHub Issue
Given a link, #number, or direct text description of a GitHub issue, resolve it end-to-end: understand the ask, verify it still applies, plan the change, implement it in small reviewable steps, and leave it ready for the user to test and commit.
Process
-
Fetch or accept the issue. If the user provided the issue details or description directly, use that information. Otherwise, fetch the issue using
gh issue view <ref> --json number,title,body,labels,comments,state— where<ref>accepts a full URL or a bare number when run inside this repo. Read title, body, and comments; comments often carry scope clarifications made after filing. Ifghisn't authenticated, ask the user to paste the issue text instead of guessing its contents. -
Pull in linked context. Per
code-review-findings/stabilization-plan.md's issue-authoring convention, issue bodies here are usually copied verbatim from acode-review-findings/NN-*.mdfinding and may point at adocs/design/*.mddoc for the concrete spec — e.g. Stage B issues linkdocs/design/authorization.md's# Implementation Plansection for schema/DDL/queries. Follow every link and file reference in the body before writing code. If the issue is one of the plan's numbered checkboxes, that entry is also useful context (dependencies, ordering, "Definition of done"). -
Re-verify against current code — don't trust the issue text blindly. Same discipline as triaging a review finding: read the actual current code first (
AGENTS.md's "verify the claim against the actual code first" rule). An issue can be stale — already fixed, the code moved, or the described mechanism no longer exists. If it no longer applies, say so and stop instead of manufacturing a change. If the issue's own "Recommendation" predates a later architectural decision (e.g. it assumes pre-Stage-B tenancy/auth), flag the conflict and propose the up-to-date approach instead of following it verbatim. -
Check dependencies. If the issue names prerequisite issues or touches code that another in-flight change is mid-rewriting, confirm those have actually landed before proceeding. If not, flag it and ask before continuing.
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.
- 10d ago First seen · 38 lines · 65 tokens per session scan A 16d93c68e09e
fix-issue is a skill published in the GitHub repository AndreiBozantan/svelte-axum-template (2 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 1,111 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
hotpath_bump
Bump the hotpath version number across the workspace and related files. Updates crate versions in Cargo.toml files (exact patch version) and version references in the backend middleware, hotpathinit skill, and README (major.minor only). Use when the user wants to bump, bump the version, or release a new hotpath…
issue-triage
Read all open issues (GitHub/GitLab), categorize by type and effort, plan batch implementation order, and coordinate implementation across multiple issues in a single PR/MR. Auto-detects platform from git remote. Use when asked to "implement all issues", "fix all open issues", "batch implement", or "address all…
stacked-prs
Optional workflow for large features using stacked PRs via gh-stack. Use ONLY when a feature has 3+ distinct concerns with clear dependencies. NOT for bug fixes, hotfixes, or small changes. Requires GitHub. Triggers: "stacked PRs", "gh stack", "split into layers", "stack this".
atomic-commit
Atomic git workflow - validates, commits, pushes, creates PR/MR, and verifies CI with zero-warnings policy. Orchestrates complete code submission as state machine with rollback on failure. Supports GitHub (gh) and GitLab (glab). Triggers: "commit changes", "push and create PR", "submit code", "atomic commit".
self-fix-loop
Self-learning fix loop - commit, push, monitor CI, auto-fix failures using swarm agents with skills on demand, loop until all checks pass. Supports GitHub Actions and GitLab CI. Use when CI fails and you need to iteratively fix until green. Triggers: "fix CI", "loop until green", "auto-fix failures", "self-fix".
test-rust
Run the complete test suite for a Rust project including unit tests, integration tests, doc tests, and coverage. Use nextest for parallel execution. Use when running tests, debugging failures, or checking coverage. Triggers: "run tests", "cargo test", "test suite", "coverage".