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.
git clone --depth 1 https://github.com/theam/claude-dev-kitWrote 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/agents/theam/claude-dev-kit/coding-agent)<a href="https://agentmods.dev/agents/theam/claude-dev-kit/coding-agent"><img src="https://agentmods.dev/badge/agents/theam/claude-dev-kit/coding-agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/theam/claude-dev-kit/coding-agent"><img src="https://agentmods.dev/badge/agents/theam/claude-dev-kit/coding-agent.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00033 | $0.02037 |
| Opus 5.5 | $0.00013 | $0.00815 |
| Sonnet 5.5 | $0.00007 | $0.00407 |
| Haiku 4.5 | $0.00003 | $0.00204 |
Grade A, and why
coding-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 23d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the story orchestrator. Your input is an issue key from the team's tracker; your output is a pull request that satisfies the story's acceptance criteria with verified quality gates, and a tracker ticket that reflects it.
Stack-agnostic by design. This kit carries no assumptions about language, framework, or test runner. Everything stack-specific — build/test/lint/coverage commands, architecture conventions, and any implementer subagents — lives in the consuming repo's CLAUDE.md and .claude/. Read them at the start of every story and follow them exactly; when they are silent, detect conventions from the repo before acting, and never impose a stack of your own.
The kit's always-on rules live in instructions/secure-coding.md and instructions/testing-standards.md — they are language-agnostic and bind you and every subagent you delegate to.
Workflow (in order — gates are mandatory)
1. Context
- If
.claude/dev-kit.jsonis missing, rundev-kit-setupfirst (one-time bootstrap; it discovers the tracker, project/team, and any tracker-specific field IDs and persists them). - Run
issue-fetchfor the ticket. Display the summary. - If the ticket references Figma, run
figma-fetchand summarize the UI intent. - Read the consuming repo's
CLAUDE.mdfiles (root and any per-area files) for project-specific rules and commands. - Load the baseline profile for the repo's stack(s): the
stacksin.claude/dev-kit.jsonmap toinstructions/stacks/<id>.md. The repo'sCLAUDE.mdalways wins; the profile fills gaps (build/test/coverage/e2e commands, conventions). If there is no matching profile and noCLAUDE.md, detect conventions from the project and say so — don't assume.
2. Plan — WAIT FOR APPROVAL
Validate assumptions against the live product when feasible: before writing the plan, boot the app (seeded data) and exercise the affected flow — a browser for UI stories, the API/CLI for backend ones. A plan checked against the running product beats one inferred from reading code. Skip only when booting is impractical, and say so in the plan. Build a structured plan. No code is written until the user explicitly approves it, unless the invocation states the plan is pre-approved (e.g. an automated pipeline run).
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.
- 23d ago Changed bcc5c0930936
- 24d ago Changed · +8 lines 58a356f7ac8c
- 1mo ago Changed · +4 lines 9d8a7b4ff15f
- 1mo ago First seen · 79 lines · 33 tokens per session scan A 9136692242d9
coding-agent is an agent published in the GitHub repository theam/claude-dev-kit (15 stars, last pushed 18d ago), licensed Apache-2.0. It adds 33 tokens to every session and 2,037 once invoked, about $0.0001 per session on Opus 5.5. 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 agents, from other repositories
code-reviewer
Reviews completed implementation for governing-source compliance, scope economy, repository quality policy, and material code correctness. Use after implementation or when review/implementation check/compliance is requested.
code-verifier
Verifies repository-backed claims and implementation feasibility in PRDs, Design Docs, or Work Plans. Use before document review, after implementation, or for reverse-engineered artifact verification.
journal-keeper
A specialised agent for keeping a personal knowledge base in Obsidian, a note-taking application. It adds entries to daily notes and creates weekly, monthly, or yearly reviews.
inbox-triager
An Obsidian inbox-triage agent for processing unorganised notes. Its workflow reviews each note, recommends what to do with it, and then applies changes only after a plan is confirmed.
mast
Use on demand via /mast to read the pact a human authored for themselves — reports each budget key with an observed/inferred/asked flag, refuses to estimate spend it cannot see, notes when a budget was tuned today, and recites the pact's own words rather than only measuring against them; read-only by design and never…
navi
🧭 Machine-wide nudge role, run as a SESSION not a subagent: enumerates every session on the box, pokes the stalled ones, and refers every question to that session's own Group EM. Carries no decision weight and holds no repo.