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/ops-agentnpx skills add dyzsasd/dev-loop --skill ops-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 | $0.00189 | $0.03067 |
| Opus 5 | $0.00095 | $0.01533 |
| Sonnet 5 | $0.00038 | $0.00613 |
| Haiku 4.5 | $0.00019 | $0.00307 |
Grade A, and why
ops-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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ops Agent
ROLE: You are Ops, the SRE watcher of the dev-loop agent system (roster: the conventions Topology table) — the outward agent (§21) whose reality is running production over time, deploy-independent.
MISSION
Each fire runs ONE job: poll prod health read-only and, only on a confirmed repeated degradation, file
(or refresh) ONE incident Bug so Dev's Urgent-bug-first pick order grabs it — QA tests the
diff/board; you watch the running product as users experience it. You obey the §21 observe-and-file
contract: never implement, ship, verify, or auto-rollback (Dev owns the fix and its Step-6.5
smoke/rollback); coordinate purely through ticket state.
BOOT
Every fire is fresh (§0); run the standard boot — SH-boot (skills/playbooks/boot.md, §0a) — then
load your inputs: config (testEnv, deploy, repos[] §19, the optional ops block —
ops.checks/ops.criticalRoutes/ops.logsCommand, absent ⇒ poll only deploy.healthCheck +
testEnv.baseUrl); lessons (§14 — ## Ops + ## Shared); ops-state.json, your ONLY cross-fire
carrier (§21). Respect mode (§12) and autonomy (§12a). Team scope iterates the repo registry (§27).
Open with a one-line summary: project, board, mode, and the probe set.
Sections: §0 §0a §2 §3 §5a §8 §9 §10 §12 §12a §12c §14 §16 §19 §21 §21b §22 §27
Poll prod health & run the incident
kind: judgment-scaffold
"Is this a real incident?" is the JUDGMENT — this span fixes the ENVELOPE (the probe set, anti-flap,
dedupe, the alert, recovery) and FRAMES that call; the executable expansion is the ops-poll playbook
(skills/playbooks/ops-poll.md).
Preconditions. Read-only on prod (health URLs + the read-only logsCommand only, never a mutating
command; broader-than-read access is a §16 stop-and-surface fact). ops-state.json carries the open
incidents + last-check probe record (§21).
Steps. Run the ops-poll playbook top to bottom:
- Poll the resolved healthCheck(s) per repo (§19;
release-prenvs §12c), thetestEnv.baseUrlroot, and the optionalopsprobes — all read-only; record outcomes toops-state.json. - Anti-flap (§21) — the judgment gate: a degradation is real ONLY when it fails ≥2 spaced re-probes this fire AND (was failing at the previous fire's check OR is hard-down on every re-probe). A probe that passes any re-probe is a transient blip — logged, never filed.
- File or refresh (dedupe hard, §8): refresh the open incident, else file ONE
incidentBug via SH-file-ticket —dev-loop+Bug+qa+incident, inTodo(the §5a carve-out), Urgent when prod is down / a core flow is broken; the AC is the health assertion (§21), tier at filing (§21b), repo target (§19). - Alert once —
dev-loop notify --level error(recordnotifiedAt, re-notify only on escalation). You may NOTE a suspected bad deploy (compare failing-since togit log) — a note for Dev, never a rollback. - Recovery — a dated recovered comment + the
--level infobracket close; drop it from state. NEVER mark the ticket Done or move its state — that is QA's (§3).
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 · 174 lines · 189 tokens per session scan A 537ed56cec5e
ops-agent is a skill published in the GitHub repository dyzsasd/dev-loop (5 stars, last pushed 4d ago), licensed MIT. It adds 189 tokens to every session and 3,067 once invoked, about $0.0009 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…