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/dev-loop-operatornpx skills add dyzsasd/dev-loop --skill dev-loop-operatorgit 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 | $0.00114 | $0.02451 |
| Opus 5 | $0.00057 | $0.01226 |
| Sonnet 5 | $0.00023 | $0.00490 |
| Haiku 4.5 | $0.00011 | $0.00245 |
Grade A, and why
dev-loop-operator 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 yesterday.
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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dev-loop operator handbook (harness-neutral)
This directory is dev-loop's first-class distributable: pure markdown + pure shell. Any
harness that can run a shell — Claude Code, Codex, opencode, or a plain terminal — loads this
skill and gets the whole operator surface. The engine is the npm package @dyzsasd/dev-loop;
this skill installs it, not the other way round. The Claude plugin
(dev-loop install-claude-plugin) is an optional convenience for /dev-loop:* slash commands.
Architecture in one minute. Nine stateless agents are fired one at a time by the in-package
scheduler dev-loop run; each fire is a one-shot claude -p / codex / opencode process whose
prompt inlines the agent's SKILL + conventions slice from the package — a machine needs only the
npm package and a logged-in coding CLI. Truth lives in the workspace: dev-loop.json (config,
env-var NAMES only), .dev-loop/hub.db (board), .dev-loop/team/fires.jsonl (cost + health).
§1 Environment check & install (first on every new machine)
bash "$(dirname "$0")/scripts/ensure-install.sh" # from this skill's directory
DEVLOOP_VERSION=1.15.1 bash scripts/ensure-install.sh # pin
DEVLOOP_INSTALL_SOURCE=/path/to/dev-loop-x.y.z.tgz bash scripts/ensure-install.sh # tarball / URL
DEVLOOP_INSTALL_SOURCE=/path/to/dev-loop-checkout bash scripts/ensure-install.sh # git checkout
Idempotent: ① node ≥ 23.6 (DEVLOOP_NODE=/abs/node honored); ② a coding CLI on PATH (claude |
codex | opencode) + login hints; ③ engine via a 3-tier source — DEVLOOP_INSTALL_SOURCE →
npm i -g @dyzsasd/dev-loop@<pin> --ignore-scripts → git clone + npm ci --ignore-scripts +
npm run build + npm i -g ./hub; ④ python3 security/source_integrity.py --whole-tree when a
source tree is at hand (labelled skip otherwise); ⑤ prints the export PATH=… line if npm's global
bin is off PATH; ⑥ dev-loop doctor, then 环境就绪 ✔ / ready. The one step that cannot be
scripted: CLI login is interactive — run claude / codex login / opencode auth login once.
What ships with it
4 files 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.
- yesterday First seen · 158 lines · 114 tokens per session scan A a73c46ab3182
dev-loop-operator is a skill published in the GitHub repository dyzsasd/dev-loop (5 stars, last pushed 4d ago), licensed MIT. It adds 114 tokens to every session and 2,451 once invoked, about $0.0006 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…