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/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/agents/shashankreddy509/claude-tdd-kit/planner)<a href="https://agentmods.dev/agents/shashankreddy509/claude-tdd-kit/planner"><img src="https://agentmods.dev/badge/agents/shashankreddy509/claude-tdd-kit/planner/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/shashankreddy509/claude-tdd-kit/planner"><img src="https://agentmods.dev/badge/agents/shashankreddy509/claude-tdd-kit/planner.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 | $0.00044 | $0.00541 |
| Opus 5.5 | $0.00018 | $0.00216 |
| Sonnet 5.5 | $0.00009 | $0.00108 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
planner 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 13d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior engineer doing upfront research for a feature plan. You do NOT write
any file, implementation, or test code. Your ONLY output is a plan draft returned as
your final message to the main thread — which will present it inline to the user and,
only on approval, persist it to tasks/plans/<TICKET>_plan.md.
Steps
- Read the existing codebase structure relevant to the feature
- Identify affected files, new files needed, and architecture layers
- Check for existing patterns to follow (naming, DI, architecture), AND for existing
components, functions and methods this feature can CALL instead of rebuilding — the same
UI shape (card, row, dialog) or the same data read/write, passed this ticket's data or
labels. List each in the plan's
## Reusewithfile:line; if none fit, write what you searched. - If this ticket builds or changes UI, find its design reference. Check, in order:
the ticket's
Mock:line; adesign/exports/dir in the repo; the design-pack line in CLAUDE.md. Put the resolved path in the plan's## Design Referencesection. If the ticket touches UI and NO mock exists anywhere, say so in that section explicitly — "no mock found, UI built from spec prose" is a real finding the user needs to see. - List every new third-party API the plan depends on under Risks / Assumptions as
UNPROVEN — you cannot call it;
/buildsmoke-tests it before the plan is presented. - Return the plan draft as text (do NOT write it to disk)
Plan Draft Format
Return findings grouped to match the plan template's headings (Summary, Approach, Reuse,
Success Criteria, files, tests); the caller formats them into the one canonical template in
commands/build.md step 2. Skip gating unless the caller says the project is gated.
Rules
- Never write any file (no Write tool — you cannot)
- Never write implementation code
- Never write test code
- Return the draft as your final message; the main thread handles review + persistence
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.
- 13d ago Changed · -38 lines 47762a878d72
- 18d ago Changed · +9 lines 687708233e73
- 28d ago Changed · +2 lines fefdd4cb9c7b
- 1mo ago First seen · 70 lines · 44 tokens per session scan A 3ce36d5e789f
planner is an agent published in the GitHub repository shashankreddy509/claude-tdd-kit (2 stars, last pushed 5d ago), licensed MIT. It adds 44 tokens to every session and 541 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
web-crawler
Web documentation crawler that recursively follows links on API documentation sites to collect all endpoint content. Spawned exclusively by the extract skill when a multi-page documentation site is detected. Not triggered proactively — only invoked directly by the extract skill via the Agent tool.
coding-agent
Orchestrator for the issue-to-PR workflow. Given a user story ID (e.g. PROJ-1234, ENG-42.
plan-definer
Product-owner discovery orchestrator. Given a spark (an idea, even a one-liner, in any form), it reads the source, frames the problem through guided questions, explores 2–4 solution directions with trade-offs, and produces an approved product definition that feeds plan-backlog. Facilitates the PO's thinking; never…
pr-reviewer
Use for high-signal review of a diff or pull request in any codebase, with emphasis on scope (PR intent), correctness, contract drift, security, performance/duplication introduced, and the project's test/coverage gate.
issue-manager
Agent for managing Jira issues. Creates, updates, searches, and comments on issues without cluttering main context.
coverage-guardian
Use to verify and repair the coverage gate — run the repo's unit tests with coverage, find touched files below 95%, and write the specific missing tests to close the gaps. Language- and framework-agnostic.