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/add-reponpx skills add dyzsasd/dev-loop --skill add-repogit clone --depth 1 https://github.com/dyzsasd/dev-loopWrote 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/dyzsasd/dev-loop/add-repo)<a href="https://agentmods.dev/skills/dyzsasd/dev-loop/add-repo"><img src="https://agentmods.dev/badge/skills/dyzsasd/dev-loop/add-repo.svg" alt="Measured on agentmods" 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 | $0.00161 | $0.01574 |
| Opus 5 | $0.00081 | $0.00787 |
| Sonnet 5 | $0.00032 | $0.00315 |
| Haiku 4.5 | $0.00016 | $0.00157 |
Grade A, and why
add-repo 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 5d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
add-repo — register a repo into a workspace project (one pass)
ROLE: You are the operator-present setup skill that makes a git repo a first-class member of a workspace project in one DETECT → INTERVIEW → REGISTER → MAP pass.
MISSION
After this skill, dev-loop doctor is green and the repo is clonable, buildable,
deployable within policy, and mapped into the project's strategy doc.
BOOT
Operator-present, but each invocation is fresh (§0); boot per §0a (the Topology block + the sections cited below). Inputs:
- The workspace
dev-loop.json(1.x workspace schema), resolved from cwd — none ⇒ tell the user todev-loop team initfirst and stop. Target project missing ⇒ run /dev-loop:add-project first. references/config-schema.md(registry/reference field shapes).- Conventions context: claiming/worktrees (§7), landing + auto-merge (§12b/§12c), multi-repo registry + doc-home (§19), workspace portability (§27). Sections: §0 §0a §2 §4 §7 §12b §12c §19 §20 §27
JOBS
1. DETECT — identify the repo and where it goes
- Ask (or take from args): the project key, a short repo ref (lowercase, the
registry key AND the
repo:<ref>label — must not collide with a reserved name: team/lessons/wt/locks), the role (primaryfor the main service,docs, or omit), and either a--remotegit URL to clone or an existing path already inside the workspace. - If a remote is given and the target dir does not exist:
git clone <remote> <workspace>/<ref>. If a path is given, confirm it is INSIDE the workspace (relative path); a repo outside the workspace breaks the copy-the-folder portability rule (§27) — offer tomvit in.
2. INTERVIEW — build, merge checks, deploy (auto-detect first, confirm with the operator)
- Build/typecheck: read
package.jsonscripts (build,typecheck/tsc), or the repo's equivalent. Propose--typecheck-cmd/--build-cmd; confirm. - Merge checks: parse
.github/workflows/*for the required PR check names (thename:of jobs that run onpull_request). These become--merge-checkvalues — the gateautoMergepolls (§12c). List them; let the operator prune. - Landing (§12b):
pr(default; agent opens a PR, CI is the build gate) ordirect. Ifpr+--auto-merge, the agent merges its own PR once checks are green (§12c). - Ops probes (don't skip — an unprobed deploy is invisible to ops-agent, doctor W07):
ask for the repo's health endpoint (probe it live once to confirm a 2xx before
recording), an optional version endpoint, the critical user-flow routes the operator
declares "can't be down", and an optional read-only logs/metrics command. Persist via
--ops-check <url>/--critical-route <path>/--logs-command "<cmd>". - Deploy: interview the deploy shape (
release-pr/command/ none) PER environment. Enforce the teamdeployPolicyceiling: ifdeployPolicy.<env> = "manual", that env may NOT beauto:true— the validated write (below) will reject it (E06); surface it before writing.
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.
- 5d ago First seen · 109 lines · 161 tokens per session scan A 983e824ac4cd
add-repo is a skill published in the GitHub repository dyzsasd/dev-loop (5 stars, last pushed 3d ago), licensed MIT. It adds 161 tokens to every session and 1,574 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…