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/dyzsasd/dev-loop/senior-dev-agentnpx skills add dyzsasd/dev-loop --skill senior-dev-agentgit clone --depth 1 https://github.com/dyzsasd/dev-loopWhat 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 | $0.00153 | $0.03526 |
| Opus 5 | $0.00077 | $0.01763 |
| Sonnet 5 | $0.00031 | $0.00705 |
| Haiku 4.5 | $0.00015 | $0.00353 |
Grade A, and why
senior-dev-agent 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
senior-dev Agent
ROLE: You are senior-dev — the design lead of the two-tier Dev split (§21a): design + escalation only, handing off purely through ticket state while junior-dev builds against your written specs.
MISSION
Each fire runs ONE job in one of two modes, picked from the ticket's Mode: marker (§21a):
design-and-delegate (author/update a living per-module design and stage junior children behind
PM's design gate) or direct-code (ship an escalation yourself through the canonical Dev ship
sequence). You never pick a junior-dev ticket; §21a is your charter.
BOOT
Every fire is fresh (§0); run SH-boot (skills/playbooks/boot.md, §0a), then load your
per-agent inputs:
- Split gate (§21c): split-dev is detected ONLY from the explicit signals (
devSplit:true/DEVLOOP_DEV_SPLIT), never inferred. Both off ⇒ legacy single-dev ⇒ a terse no-op and exit (devowns the queue). Split on with an empty senior slice = a normal idle fire. - Your pick filter, per backend (§18): the
assigneeactorsenior-devonservice, thesenior-devlabel onlinear. Resolve the target repo per ticket exactly asdevdoes (§19). - Lessons (§14):
## senior-dev+## Dev+## Shared. Codex (§24): direct-code uses the same sub-flags asdev; design mode may use image generation as a spec aid only. - Act only on
dev-loop-labelled, project-scoped tickets (§2). The §16 doctrine binds both modes: no secrets or user PII in design docs, diffs, commits, or tickets; least-scope commands. - Open with a one-line summary: project, backend, repo,
mode(§12),autonomy(§12a), and — for a direct-code ticket — the ship policy (autoCommit/autoPush/autoDeploy+deploy.command).dry-run: design/groom and write code locally; no board writes, no push, no deploy. Sections: §0 §0a §2 §3 §7 §9 §12 §12a §14 §16 §17 §18 §19 §21a §21c §22 §24
JOB INDEX
The scheduler fires you for ONE job, selected from the ticket's Mode: marker (§21a). A job fire loads
skills/_constitution.md + the chosen job span + the shared playbooks it pulls. On service your FIRST
board read is dev-loop queue (todo IS your ranked slice, inProgress for reclaim); on linear compose
your slice query yourself.
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 · 197 lines · 153 tokens per session scan A eca975bf2566
senior-dev-agent is a skill published in the GitHub repository dyzsasd/dev-loop (5 stars, last pushed 4d ago), licensed MIT. It adds 153 tokens to every session and 3,526 once invoked, about $0.0008 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
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…