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/commands/shashankreddy509/claude-tdd-kit/build)<a href="https://agentmods.dev/commands/shashankreddy509/claude-tdd-kit/build"><img src="https://agentmods.dev/badge/commands/shashankreddy509/claude-tdd-kit/build.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 5.1 | $0.00000 | $0.02677 |
| Opus 5 | $0.00000 | $0.01339 |
| Sonnet 5 | $0.00000 | $0.00535 |
| Haiku 4.5 | $0.00000 | $0.00268 |
Grade A, and why
build 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 7d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan a new feature inline, iterate until approved, then auto-hand off to implementation.
This command runs in the MAIN thread (not a subagent) so the plan is shown to you directly in chat and you can iterate on it in real time. No plan file is written until you explicitly approve.
Feature request: $ARGUMENTS
Flow
0. Triage-file check (bug path) — DO THIS FIRST
- Derive the ticket key from
$ARGUMENTS(e.g.<KEY>) if one is present. - If a key is present, check for
tasks/<TICKET>-triage.mdin the open project (a triage artifact from any bug-triage workflow). If it exists, this is a bug fix with a confirmed root cause — do NOT re-explore from scratch:- Read the triage artifact. Trust its stated verdict, root cause, affected files, what it excluded as adjacent, and any fix-plan seed it proposes.
- If the verdict is
not-reproducible/invalid/pre-existing, STOP and tell the user — there is nothing to build; surface the triage recommendation (close it / not our change). - If
real-bug, write a LEAN fix-plan: the smallest correct change at the shared point (not per-caller), the one test from the seed, and the toggle gate if the seed names one. Skip the broad exploration in step 1 — the root cause is already proven. Present it inline (step 2), iterate (step 3), and on approval (step 4) write it as the plan file.
- If no triage file, this is the normal feature/plan path — continue to step 1.
0.5. Automation admissibility check (OPTIONAL — requires an automation-approval gate)
- Is this request a DURABLE AUTOMATION — a cron/scheduled job, a hook, a mirror/sync, a recurring report, or a new always-on surface? If no, continue to step 1.
- If yes AND your setup has an automation-approval gate, confirm it approved this process before planning; a rejected verdict → STOP and report it, since planning a build the gate rejected defeats the gate.
- No such gate installed → continue to step 1. This check must never block a build.
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.
- 7d ago First seen · 179 lines · 0 tokens per session scan A a8a71282ec54
build is a command published in the GitHub repository shashankreddy509/claude-tdd-kit (2 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,677 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
workflow-classify
Classify task size (S/M/L/XL) and recommend the appropriate workflow pipeline.
slack-gif-creator
Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
rewind-summary
Capture a carry-forward summary of work done since a checkpoint so it survives a native rewind/Restore. Run before rewinding.
analytics-review
Review analytics and recent commits, then create tasks.
implement
Deep, autonomous end-to-end development workflow -- target verification, project discovery, Obsidian history, architecture/UX (when needed), research, implementation, testing, visual QA (when available), security/performance/final review, Definition of Done, persistent resumable state, Obsidian write-back.