Borrowing it
Nothing to install: this file belongs to datris/datris-platform-oss. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/datris/datris-platform-oss/main/.claude/commands/lead.mdgit clone --depth 1 https://github.com/datris/datris-platform-ossWrote 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/datris/datris-platform-oss/lead)<a href="https://agentmods.dev/commands/datris/datris-platform-oss/lead"><img src="https://agentmods.dev/badge/commands/datris/datris-platform-oss/lead/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/commands/datris/datris-platform-oss/lead"><img src="https://agentmods.dev/badge/commands/datris/datris-platform-oss/lead.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 | $0.00026 | $0.00887 |
| Opus 5.5 | $0.00010 | $0.00355 |
| Sonnet 5.5 | $0.00005 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
lead 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 1mo 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the lead. Drive the story at $ARGUMENTS to a reviewed pull request. You delegate; you
do not implement or review yourself.
0. Load the story
- If the argument is a GitHub issue URL,
gh issue view <url> --json title,body -q .bodyand save it toplans/stories/issue-<number>.md. Otherwise read the file. - Refuse if any required section is missing. Print which, and stop.
- Extract Branch from the story.
1. Claim and branch
git status --porcelainmust be empty. Stop if not.git checkout main && git pull --ff-only, thengit checkout -b <branch>(orgit checkout <branch>if it exists and is ahead of main only by story commits).- Set the story's Status line to
claimed.
2. Specs first
Spawn tester in mode specs with the story path. Wait. Note its E2E-ONLY list.
If it reports zero tests written and zero E2E-ONLY bullets, stop: the story's Acceptance section
is too vague to build against. Print that and return the story to proposed.
3. Implement
Spawn implementer with the story path, the branch, and the tester's TESTS list, with the
instruction "make these pass; do not delete or weaken them". Wait for its report.
STATUS: blocked→ set story Status toproposed, print the report, stop.
4. Review loop (max 3 rounds)
Spawn reviewer with the story path. Wait.
VERDICT: PASS→ go to 5.VERDICT: FAIL→ continue the same implementer agent (SendMessage by its ID) with the reviewer's FINDINGS verbatim and the instruction "fix only these, then rerun Verify". Wait, then spawn a fresh reviewer. Repeat.- After 3 FAILs → set Status to
in-review, print the last findings, stop. A human decides.
5. End-to-end (only if the story's Verify has a manual block)
Spawn a fresh tester in mode e2e with the story path. Wait.
VERDICT: FAIL→ continue the same implementer with the STEPS and ADVERSARIAL failures verbatim, then go back to 4 with a fresh reviewer. This counts toward the 3-round cap.SKIPPEDorPASS→ continue.
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.
- 1mo ago First seen · 63 lines · 26 tokens per session scan A 10d2482913e8
lead is a command published in the GitHub repository datris/datris-platform-oss (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 26 tokens to every session and 887 once invoked, about $0.0001 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 2026-09-16.
lead compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| leaddatris/datris-platform-oss | Command | 13 | yesterday | Apache-2.0 | A | 26 | Claude Code |
| infa-statusoracle-samples/oracle-aidp-samples | Command | 58 | 2d ago | UPL-1.0 | A | 50 | Claude Code |
| migrate-catalogoracle-samples/oracle-aidp-samples | Command | 58 | 2d ago | UPL-1.0 | A | 41 | Claude Code |
| migrate-joboracle-samples/oracle-aidp-samples | Command | 58 | 2d ago | UPL-1.0 | A | 38 | Claude Code |
| migration-statusoracle-samples/oracle-aidp-samples | Command | 58 | 2d ago | UPL-1.0 | A | 48 | Claude Code |
| snowflake-catalogoracle-samples/oracle-aidp-samples | Command | 58 | 2d ago | UPL-1.0 | A | 47 | Claude Code |
| check-dataoracle-samples/oracle-aidp-samples | Command | 58 | 2d ago | UPL-1.0 | A | 37 | Claude Code |