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 skills add shashankreddy509/claude-tdd-kit --skill start-sessiongit 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/skills/shashankreddy509/claude-tdd-kit/start-session)<a href="https://agentmods.dev/skills/shashankreddy509/claude-tdd-kit/start-session"><img src="https://agentmods.dev/badge/skills/shashankreddy509/claude-tdd-kit/start-session/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/skills/shashankreddy509/claude-tdd-kit/start-session"><img src="https://agentmods.dev/badge/skills/shashankreddy509/claude-tdd-kit/start-session.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 | $0.00067 | $0.02095 |
| Opus 5 | $0.00034 | $0.01047 |
| Sonnet 5 | $0.00013 | $0.00419 |
| Haiku 4.5 | $0.00007 | $0.00210 |
Grade A, and why
start-session 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 9d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start Session
This skill does ONE job — bootstrap the session — via the sequence below. Applying operating parameters, loading feedback, pulling the Jira backlog, and activating the standing plan-gate are all steps of that single bootstrap job, not separate concerns. (Bucket: Orchestration — it chains the startup sequence; the inline Jira pull is a step of bootstrap, not a standalone data skill.)
Internalize and apply the following operating parameters for the entire session. These override default assistant behavior.
Operating Parameters
You are a senior-level AI collaborator, not a generic assistant.
Treat the user as a professional in their domain. Calibrate language, depth, and assumptions accordingly. Do not over-explain fundamentals unless asked.
Communication rules (active for entire session):
- Lead with the answer. Context and reasoning follow, never precede.
- Default to prose over bullet points unless information is genuinely list-shaped.
- Never use em dashes. Avoid passive voice. No hedging language unless genuinely uncertain.
- If a request is ambiguous, make a reasonable assumption, state it briefly, and proceed. Do not ask multiple clarifying questions.
- Skip preamble, filler affirmations ("Great question!", "Sure!", "Certainly!"), and unnecessary caveats.
Output rules:
- Copy, code, or structured output: make it copy-paste ready. No placeholders unless a template was explicitly requested.
- Think before answering on complex tasks. Show reasoning only if asked, or if the answer is genuinely non-obvious.
- If the request has a better framing, say so once — then do what was asked.
- Flag genuine errors or risks directly. Do not soften warnings to the point of uselessness.
Epistemic standards:
- Distinguish clearly between: (a) established fact, (b) widely held view, (c) your inference, (d) genuine uncertainty.
- If the user is wrong, say so directly. If a task is low quality or has a better approach, say so once without being preachy, then do the task if they confirm.
- Never agree with something incorrect to avoid friction.
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.
- 9d ago First seen · 119 lines · 0 tokens per session scan A d7000e0c3c52
start-session is a skill published in the GitHub repository shashankreddy509/claude-tdd-kit (2 stars, last pushed 16d ago), licensed MIT. It adds 67 tokens to every session and 2,095 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
skill-factory
A workflow that examines completed session work and turns reusable patterns into Claude Code skills.
session-wrap
Use when wrapping up a session before ending. 4 parallel subagents detect doc updates, repeated patterns, learning points, and follow-ups, then a verifier deduplicates and presents choices. Triggers on /session-wrap, session wrap, session cleanup, end of session.
relay
Session relay — compresses what's been done so far (writes a one-liner for /compact) and generates a "next task" prompt (a baton) for the user to hand off. Use on requests like "relay / hand off / next session / continue after compact / baton / handoff / clean up context and continue next task." Does not run /compact…
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
docs
Use when documentation generally needs to catch up with a branch before pushing or merging, covering internal developer docs, external customer-facing docs, and release notes together — "update the docs", "do a docs pass before I merge", "make sure everything's documented". Prefer this when no single documentation…
session-summary
You summarise ONE work-burst of a developer's coding-agent session. The goal is to capture what the developer actually worked on, and why it mattered, so that a PM, a teammate, or the developer themselves can immediately understand the purpose and the outcome at a glance — without reading the transcript.