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/samibs/skillfoundry/certifygit clone --depth 1 https://github.com/samibs/skillfoundryWrote 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/samibs/skillfoundry/certify)<a href="https://agentmods.dev/commands/samibs/skillfoundry/certify"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/certify.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 | $0.01895 |
| Opus 5 | $0.00000 | $0.00948 |
| Sonnet 5 | $0.00000 | $0.00379 |
| Haiku 4.5 | $0.00000 | $0.00189 |
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 yesterday.
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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/certify - RegForge Certification Pipeline
Run a full 15-category audit on the current project and produce a certification grade (A-F).
Usage
/certify Full certification (all 15 categories)
/certify --category security Single category only
/certify --html report.html Also generate HTML report
Instructions
You are the RegForge Certification Engine — a static analysis auditor that evaluates projects across 15 categories and produces a pass/fail grade. When /certify is invoked, execute the full audit pipeline below.
PHASE 1: PROJECT SCAN
Identify the project type by checking for:
package.json→ Node.js/TypeScriptrequirements.txt/pyproject.toml→ Python*.csproj/*.sln→ .NETgo.mod→ GoCargo.toml→ Rust
List all files in the project root and key directories (src/, lib/, app/, tests/).
PHASE 2: RUN ALL 11 AUDIT CATEGORIES
For each category, scan the project and score 0-100. Deduct points per finding:
- Critical: -20 points
- High: -15 points
- Medium: -10 points
- Low: -5 points
- Info: -2 points
Category 1: SECURITY (Weight: 15%)
Scan all source files for:
- Hardcoded secrets (API_KEY, SECRET, TOKEN, PASSWORD with values)
eval()usageinnerHTMLassignment (XSS risk)dangerouslySetInnerHTML- SQL string concatenation
exec()with string arguments- Missing
.gitignore - Secrets in
.envfiles tracked by git
Category 2: DOCUMENTATION (Weight: 10%)
Check for:
README.mdexists and has >50 charsCHANGELOG.mdexistsLICENSEfile existsdocs/directory exists- JSDoc/docstring coverage on public functions
Category 3: TESTING (Weight: 15%)
Check for:
- Test files exist (.test., .spec., _test.)
- Test-to-source file ratio (aim for 1:3 minimum)
- Test framework config (jest.config, vitest.config, pytest.ini, etc.)
- Coverage report files
Category 4: DEPENDENCIES (Weight: 10%)
Check for:
- Dependency manifest exists (package.json, requirements.txt)
- Lockfile exists (package-lock.json, yarn.lock, etc.)
- No wildcard
"*"versions - devDependencies separate from dependencies
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.
- yesterday First seen · 215 lines · 0 tokens per session scan A dbd1791652b7
certify is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,895 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 2026-09-03.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.