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 commands/shashankreddy509/claude-tdd-kit/implementgit clone --depth 1 https://github.com/shashankreddy509/claude-tdd-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/commands/shashankreddy509/claude-tdd-kit/implement)<a href="https://agentmods.dev/commands/shashankreddy509/claude-tdd-kit/implement"><img src="https://agentmods.dev/badge/commands/shashankreddy509/claude-tdd-kit/implement.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 | $0.00000 | $0.00930 |
| Opus 5 | $0.00000 | $0.00465 |
| Sonnet 5 | $0.00000 | $0.00186 |
| Haiku 4.5 | $0.00000 | $0.00093 |
Grade A, and why
implement 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 3d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spawn the build-coordinator agent to execute the full TDD pipeline against an approved plan.
Plan path: $ARGUMENTS
Precondition: an approved plan file must exist at tasks/plans/<TICKET>_plan.md.
- If a path is given in $ARGUMENTS, use it.
- If none is given, default to the most recently modified
tasks/plans/*_plan.md. - If no such file exists → STOP and tell the user to run this plugin's
buildcommand first and approve a plan. - State which plan file you resolved; if the user named a ticket and the resolved file doesn't match it, STOP and ask.
Approval gate (runs only if ~/projects/agent-office/tools/gate.py exists; otherwise skip silently — behaviour unchanged)
A plan FILE is not an approval. Check the durable record for this exact version of the file:
run python3 ~/projects/agent-office/tools/gate.py check <resolved-plan-path> and act on stdout:
approve→ proceed.discard→ STOP: this plan was discarded; name the recorded timestamp. Never build a discarded plan, whatever its mtime says.revise→ STOP: a revision was requested and the plan has not been rewritten since. Tell the user to finish the revise (the rewrite reopens the gate).unanswered→ no recorded approval for this version. If$AGENT_OFFICE_GATEisfloor, runpython3 ~/projects/agent-office/tools/gate.py wait <resolved-plan-path> --timeout 600and act on its outcome as above (timeout→ ask below). Otherwise ask viaAskUserQuestion("Build this plan?" — Approve / Cancel); on Approve runpython3 ~/projects/agent-office/tools/gate.py record <resolved-plan-path> approveso the answer is durable, on Cancel recorddiscardand STOP. This closes the hole where the newest plan file gets built with nobody on record approving it.
Step 0 — Move Jira ticket to "In Progress" (if a ticket is in scope)
Before spawning the build-coordinator, derive the Jira ticket key from the resolved
plan file (e.g. <KEY> from tasks/plans/<KEY>_plan.md).
- If a key is present, resolve the Jira MCP dialect FIRST — see
references/jira-mcp.md. It returns the tool names to use and whethercloudIdis a parameter on this machine. No Atlassian MCP resolved → log the skip line from that file and proceed to the build; the pipeline does not depend on Jira. - Look up the ticket's available transitions with the resolved list transitions tool.
- Find the transition whose
to.nameis exactly"In Progress"(a Jira convention, not a per-project id). If no such transition exists, log a one-line note (": no 'In Progress' transition in this project's workflow — skipping") and proceed. Do not break the pipeline on Jira weirdness. - Apply it with the resolved transition tool, passing that id.
- On a 400, read the error body: "transition not available/valid from the current status" means the ticket is already in or past In Progress — log the no-op and proceed. Any OTHER error (auth, permissions, project misconfig) → log a one-line warning with the error text and proceed. The pipeline must not depend on Jira being available.
- If no ticket key can be derived from the plan filename, skip this step silently.
- Log what you did, e.g. "📋 Moved → In Progress" or "📋 already past In Progress, no transition needed".
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.
- 3d ago First seen · 58 lines · 0 tokens per session scan A 3dc132916b42
implement is a command published in the GitHub repository shashankreddy509/claude-tdd-kit (2 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 930 tokens. 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 commands, from other repositories
tdd-requirements
TDD開発の要件整理を行います。機能要件を明確化し、テスト駆動開発のための準備を行います。.
spec-impl
Execute spec tasks using TDD methodology.
task-verify
PitWay: Run an inprogress task's approved verification command and persist evidence.
task-discard
PitWay: Abandon a dispatched task's worktree without integrating.
eval
Evaluate and improve one healthcare agent's system prompt. Run up to 5 iterations of: prepare fixed questions -> answer -> judge -> improve -> re-score -> commit if better.
milestone-status
PitWay: Show a milestone's status, contract, progress, and tasks.