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/validatedgit 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/validated)<a href="https://agentmods.dev/commands/shashankreddy509/claude-tdd-kit/validated"><img src="https://agentmods.dev/badge/commands/shashankreddy509/claude-tdd-kit/validated.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 | $0.01071 |
| Opus 5 | $0.00000 | $0.00535 |
| Sonnet 5 | $0.00000 | $0.00214 |
| Haiku 4.5 | $0.00000 | $0.00107 |
Grade A, and why
validated 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 5d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manual-validation sign-off: record what you verified, then move the ticket from its verification column to Done.
This is Stage 5, the last of the gated pipeline (Build → Implement → Ship → Merged →
Validated). Run it after /tdd-pipeline:merged parked the ticket in a verification
column and you actually validated the change on a real build.
Triggers: /tdd-pipeline:validated <KEY> [note], e.g.
/tdd-pipeline:validated PROJ-12 verified on device, rate limiter holds under load.
This is the ONLY command in the pipeline that moves a ticket to Done. That's the point:
Done should mean validated, not merely merged. merged deliberately stops short.
Step 0 — Resolve context
<KEY>from the argument, else the newesttasks/plans/*_plan.md, else the branch name. With no key, stop and ask — this command is entirely about the ticket.- Resolve the Jira MCP dialect ONCE — see
references/jira-mcp.md. It returns the tool names for this machine and whethercloudIdis a parameter (and if so, where to read it from). No Atlassian MCP resolved → STOP and say so: this command is entirely about the ticket, so there is nothing it can do without Jira.
Step 1 — Gate on the current status
Read <KEY>'s status with the resolved get issue tool (request the status field).
- Status is a verification column ("Build Testing", "QA", "Testing", "Verify") → proceed.
- Status is already Done → say so and stop. Nothing to do.
- Status is anything earlier (To Do, In Progress, In Review) → stop. The work hasn't
been merged and parked yet; point the user at
/tdd-pipeline:mergedfirst. Closing a ticket that never reached verification is exactly what this gate exists to prevent.
If the board has no verification column at all, merged already moved the ticket to Done
and this command has no role — say so and stop.
Step 2 — Capture the validation note
The note is the record of what you checked, so it must come from the user, not be invented.
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.
- 5d ago First seen · 113 lines · 0 tokens per session scan A c9345ef1179f
validated is a command published in the GitHub repository shashankreddy509/claude-tdd-kit (2 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,071 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
create
Command "create" from freema/mcp-jira-stdio, covering /jira:create, usage, examples and what happens.
launch-story
Create a dedicated worktree for a story and open a new VS Code window on it, ready to run the pipeline. Usage - /launch-story PROJ-1234.
browse-skills
Browse all available JIRA skills with descriptions and examples.
context-new
Create a new GitHub repository with AllBeads pre-configured.
Agent Mail for real-time coordination between agents.
project-new
Plan a new project - create repo and beads, but don't code yet.