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.
git clone --depth 1 https://github.com/terrene-foundation/kailash-coc-claude-pynpx agentmods add skills/terrene-foundation/kailash-coc-claude-py/42-certifyWrote 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/terrene-foundation/kailash-coc-claude-py/42-certify)<a href="https://agentmods.dev/skills/terrene-foundation/kailash-coc-claude-py/42-certify"><img src="https://agentmods.dev/badge/skills/terrene-foundation/kailash-coc-claude-py/42-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.
<a href="https://agentmods.dev/skills/terrene-foundation/kailash-coc-claude-py/42-certify"><img src="https://agentmods.dev/badge/skills/terrene-foundation/kailash-coc-claude-py/42-certify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 8 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Tool Misuse · line 104 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 130 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Prompt Injection · line 22 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00040 | $0.05414 |
| Opus 5 | $0.00020 | $0.02707 |
| Sonnet 5 | $0.00008 | $0.01083 |
| Haiku 4.5 | $0.00004 | $0.00541 |
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 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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/certify — knowledge gate for new devs/consultants
This skill is the procedural detail for the /certify command (.claude/commands/certify.md). The command is the entry point; this skill is the runbook the orchestrator follows. Three phases — Brief → Probe → Gate, gated at 100% — behind a Phase 0 entry gate (identity + bank validation + operator consent) that MUST clear first.
When to use
- A new dev or consultant joins the repo and is about to claim their first piece of non-trivial work.
- An existing operator returns after a long absence (>30 days) and the question bank or critical-rule corpus has materially changed since their last certification.
- A repo owner wants to re-certify the whole team after a major architectural shift recorded in
specs/.
/certify does NOT replace /onboard — /onboard answers "what's the current team state" (read-only, ~5 min). /certify answers "does this person KNOW the critical surface well enough to claim work" (write-receipts + journal pass, ~30–60 min). Run /onboard first; then /certify.
Read-only vs state-write contract
/certify writes state, but a narrow set:
| Surface | Phase | Write? |
|---|---|---|
workspaces/_certify/.pending/* |
Brief | Yes — per-section read receipts (scrubbed per user-flow-validation.md MUST-6); OUTSIDE the journal/ subtree (see § note) |
| In-session probe state | Probe | No persisted file; tally lives in orchestrator context |
journal/NNNN-DECISION-certify-pass-*.md |
Pass (gate met) | Yes — committed pass receipt, under a covering codify lease |
journal/NNNN-DECISION-certify-defer-*.md |
Abandon mid-gate | Yes — deferral receipt (DECISION-typed; DEFER is not a journal-reserve.js::VALID_TYPES member), under a covering codify lease |
codify lease (codify/<display_id>-<date>) |
Pass / Abandon | Yes — acquired before the journal write, released after (§ Pass receipt Steps 1.5/5) |
posture.json |
(n/a — no posture write) | No — trust-posture machinery already enforces L2 for unrostered operators |
operators.roster.json |
(n/a — no roster write) | No — registration PRECEDES certification (the roster row already exists); pass gates /claim |
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 · 303 lines · 40 tokens per session scan A c8ecc54299f3
certify is a skill published in the GitHub repository terrene-foundation/kailash-coc-claude-py (12 stars, last pushed 24d ago), licensed Apache-2.0. It adds 40 tokens to every session and 5,414 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.
Other skills, from other repositories
gsd-milestone-summary
Generate a comprehensive project summary from milestone artifacts for team onboarding and review.
git-pr-workflows-onboard
You are an expert onboarding specialist and knowledge transfer architect with deep experience in remote-first organizations, technical team integration, and accelerated learning methodologies. You.
team-onboarding-playbook
Design a structured onboarding experience that gets new team members productive in 30, 60, and 90 days. Use when a new hire is joining, when contractors or agency partners need to ramp up, when an existing team is restructuring and members are switching focus, or when current onboarding feels chaotic and slow. Also…
product-adoption
Diagnose and design product adoption for onboarding, activation, behavior change, feature discovery, rollout, and sustained use after launch. Covers consumer, B2B, internal-tool, and public-service contexts with evidence-based decision points and cohort segmentation. Does not own acquisition campaigns or marketing…
interview-system-designer
Design hiring interviews, competency matrices, question banks, scoring rubrics, and interviewer calibration for a specified role.
sales-coaching
Sales coaching system — REKS diagnosis (Jacco van der Kooij / Winning by Design), MEDDICC deal reviews (Andy Whyte), JOLT for indecision, call coaching (Jon Barrows, Jason Bay), manager cadence (Kevin Dorsey), and founder-as-coach. Use when building coaching programs, 1:1s, deal reviews, call feedback, or improving…