certify

certify is a command for Claude Code from terrene-foundation/kailash-coc-claude-py. It costs 30 tokens per session (2,535 once invoked), scanned A, original, Apache-2.0.

A command that teaches a new developer or consultant the repository's critical knowledge and tests whether they understand it.

In plain words
What is it for?
Use it after onboarding to run a guided briefing, a knowledge probe, and a final pass-or-retry gate.
Why use it?
It prevents people from claiming work before they understand the codebase's important paths and risks.

Command for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node .claude/bin/validate-cert-bank.mjs specs/_certification.yaml.

Good fit Use it after onboarding to run a guided briefing, a knowledge probe, and a final pass-or-retry gate.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/terrene-foundation/kailash-coc-claude-py
agentmods
npx agentmods add commands/terrene-foundation/kailash-coc-claude-py/certify

Made for: Claude Code.

Wrote 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.

agentmods badge for certify

README.md
[![agentmods](https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/certify/github.svg)](https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/certify)
Your own site
<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/certify"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/certify/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.

agentmods 80×15 button for certify

Your own site · 80×15
<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/certify"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/certify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,535 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.02535
Opus 5 $0.00015 $0.01267
Sonnet 5 $0.00006 $0.00507
Haiku 4.5 $0.00003 $0.00253

Measured 7d ago against content hash 5b0c82ab97e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

certify 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.

.claude/commands/certify.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Certify the operator's knowledge of THIS repo's critical paths before they may claim work. Three phases — Brief → Probe → Gate — gated at 100% on the probe. The operator answers the gate phase SOLO (no Claude assistance); the orchestrator only walks the brief and judges answers.

Usage: /certify (no args; runs in current repo) — uses the per-repo question bank at specs/_certification.yaml.

Pairs with /onboard: /onboard is the deterministic read-path (who am I + what's the team state, read-only, ~5 min). /certify is the knowledge-gate (what does the new operator KNOW about the critical surface, ~30–60 min, write-receipts at brief + journal entry at pass). Run /onboard first; then /certify before the operator claims any non-trivial work.

Process

/certify is a structured walk-then-test. The procedure detail (brief read-order, probe presentation, gate retry loop, YAML schema) lives in the skill .claude/skills/42-certify/SKILL.md; this command is the entry point.

1. Identify the operator + confirm prerequisites

Resolve identity structurally — NOT by prose-claim. The orchestrator MUST run the following Bash invocation and parse the JSON, refusing to proceed on any non-rostered shape:

node -e 'const r = require("./.claude/hooks/lib/operator-id.js").resolveIdentity(process.cwd()); process.stdout.write(JSON.stringify(r));'

Treat as STOP (do NOT fall through to Phase A) when the parsed JSON has ANY of: verified_id == null, person_id == null, posture == "L2_SUPERVISED" AND no roster row, OR a non-zero exit code from the node invocation. On STOP, surface to the operator: "Identity check failed: you are not rostered (/whoami --register first) — /certify needs a roster row to record the pass against." Do NOT proceed prose-only; the structural Bash check IS the gate.

Registration precedes certification. resolveIdentity reads the WORKING-TREE roster (.claude/hooks/lib/operator-id.js reads operators.roster.json from disk, not from a committed ref), so an operator who has just run /whoami --register can run /certify on their still-open enrollment branch — the roster row is visible in the working tree before the PR merges — OR after merge. The roster row is a prerequisite, not a next step; certification is what gates /claim.

Read the full file on GitHub · 107 lines

Changes

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.

  1. 7d ago First seen · 107 lines · 30 tokens per session scan A 5b0c82ab97e7

Subscribe to this mod's changes

certify is a command published in the GitHub repository terrene-foundation/kailash-coc-claude-py (12 stars, last pushed 22d ago), licensed Apache-2.0. It adds 30 tokens to every session and 2,535 once invoked, about $0.0002 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 2026-09-03.