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 agentmods add skills/agentic-development/adev-plugin/bugfix-loopnpx skills add agentic-development/adev-plugin --skill bugfix-loopgit clone --depth 1 https://github.com/agentic-development/adev-pluginWhat 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 | $0.00055 | $0.06221 |
| Opus 5 | $0.00028 | $0.03111 |
| Sonnet 5 | $0.00011 | $0.01244 |
| Haiku 4.5 | $0.00006 | $0.00622 |
Grade A, and why
adev:bugfix-loop 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 2d 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomous Bugfix Loop
Announce at start: "I'm using the adev:bugfix-loop skill to drain eligible bugs from the board."
Arguments
--max-bugs <N>: caps bugs attempted across the whole run (across all self-re-invoked turns). Default: unbounded — the loop drains until no eligible bug remains or--max-turnsis hit.--max-turns <N>: caps self-re-invocation turns. Default: 20 — a conservative bound preventing an unbounded run when neither flag is set.--github-sync: enables the tracker-provider-bridge's inbound pull before each bug selection and outbound writeback after each attempt (tracker-provider-bridge.spec.md). Inbound sync runs once per turn in Step 0, before the status/budget guard; outbound writeback runs once per completed attempt in Step 4. Both degrade gracefully (never error the loop) when GitHub orghis unreachable — see Failure Modes below.--resume [--resume-run-id <id>](internal): used only by this skill's own self-re-invocation, mirroring/adev:build --resume. Not intended for direct user invocation.--resume-run-idis always passed explicitly by the re-invocation call — the skill always knows its ownrun_idfrom the turn that just completed. A manual--resumewithout--resume-run-idfalls back toadev bugfix-loop latest(the rare case of a manual--resumeafter a crash where the exactrun_idwasn't captured).--worktree-per-bug: default OFF. When set, each bug's claim,/adev:debug --autoattempt (Step 4), and any resulting commit happen inside a dedicatedadev-managed worktree (adev worktree add --slug bugfix-<issue-id> --base <ref>) instead of the shared working tree — isolating each bug's diff from every other bug's in-flight changes (spec BEH-3).--auto-commit: default OFF. When set (with or without--worktree-per-bug), aFIXEDverdict triggers Step 4.5's commit/push/PR automation (spec BEH-4). Without either--worktree-per-bugor--auto-commit, Step 4.5 is skipped entirely and behavior is unchanged from before this capability existed.--max-priority <P0-P4>: caps the priority band Step 2 selects from. Default:P3(coveringP2/P3, identical to today's hardcoded behavior). The fullP0-P4range is accepted —P0/P1are a deliberate, explicit operator opt-in (BEH-9), not rejected the way they were before the eligibility-floor amendment shipped. Validated fail-fast at Step 0, before any bug selection (BEH-10); malformed values (anything other thanP0-P4) halt the run withINVALID_PRIORITY_BOUND. BEH-7's unconditional module-exclusion floor (reserved safety tags, always enforced) is unaffected by this flag at any value, includingP0— it is the actual, non-configurable safety boundary, not the priority band.
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.
- 2d ago First seen · 249 lines · 55 tokens per session scan A 4e74c1480a38
adev:bugfix-loop is a skill published in the GitHub repository agentic-development/adev-plugin (11 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 6,221 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…