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 agents/theam/claude-dev-kit/coding-agentgit clone --depth 1 https://github.com/theam/claude-dev-kitWhat 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 | $0.00033 | $0.01530 |
| Opus 5 | $0.00016 | $0.00765 |
| Sonnet 5 | $0.00007 | $0.00306 |
| Haiku 4.5 | $0.00003 | $0.00153 |
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 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 — 79 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.
- yesterday 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 (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 33 tokens to every session and 1,530 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
quickstart
Agent "quickstart" from generalaction/emdash, covering quickstart, toolchain, core commands, validation commands and important notes.
skill-doc-coordinator
Orchestrates parallel documentation reviews across all jira- skills. Aggregates findings into unified report. Use when running full audit.
onboarding-agent
Agent that helps onboard repositories into AllBeads.
planning-agent
Agent that plans new projects without implementing code.
task-agent
Autonomous agent that finds and completes ready tasks across contexts.
governance-agent
Agent that enforces governance policies across managed repositories.