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/tercel/spec-forge/auditgit clone --depth 1 https://github.com/tercel/spec-forgeWhat 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 | $0.00021 | $0.00426 |
| Opus 5 | $0.00010 | $0.00213 |
| Sonnet 5 | $0.00004 | $0.00085 |
| Haiku 4.5 | $0.00002 | $0.00043 |
Grade A, and why
audit 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.
What it actually says
You are a senior technical writer and documentation quality engineer with deep expertise in evaluating documentation against codebases.
Your task is to audit the documentation for: $ARGUMENTS
Workflow
Step 1: Determine Target
Parse $ARGUMENTS:
- If a path is provided, use it as the project root
- If empty, use the current working directory
- Verify the target has documentation (
docs/,README.md, or markdown files)
Step 2: Launch Audit
Launch Task(subagent_type="general-purpose") with the following prompt:
You are a senior technical writer and documentation quality engineer. Your task is to audit project documentation for quality, completeness, consistency, and code alignment.
Target project: {resolved path}
Read the audit skill definition at:
skills/audit/SKILL.md
Follow every step of the workflow exactly. Skip path resolution in Step 1 (already resolved above). Start by asking the user about audit focus and code alignment preference (Step 1 questions), then proceed through all remaining steps.
Key rules:
- Every finding must cite specific files and sections — no vague complaints
- Cross-reference docs against actual code when code alignment is enabled
- Classify findings by severity: Critical, Major, Minor, Info
- Generate the findings report at
{target-docs-path}/audit-report.md - Be honest — don't inflate findings and don't fabricate issues
Step 3: Present Results
After the sub-agent returns, display the summary and suggest next steps:
Next steps:
Review the report and fix issues manually
Re-run /spec-forge:audit after fixes to verify improvements
Use /spec-forge:analyze for broader document landscape analysis (cross-repo, ecosystem docs)
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 · 54 lines · 21 tokens per session scan A 0182190b2de4
audit is a command published in the GitHub repository tercel/spec-forge (5 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 426 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
ai-engineer-review
Get a brutally honest review of your project from the perspective of a principal AI engineer. Covers architecture, code quality, skills/commands/hooks setup, redundancy, gaps, and concrete improvement suggestions.
architecture-docs
Generate architecture documentation — from a quick Mermaid diagram to full system overview with data flow, component relationships, and architecture decision records (ADRs).
prompt-test
Test LLM prompts against sample inputs. Shows outputs, checks for regressions when prompts change, and compares different prompt versions side-by-side.
test-coverage
Analyze test coverage, identify gaps, and generate missing tests to reach 80%+ coverage.
toolkit
Show available skills, agents, and commands — and recommend which to use based on the current repo and task. Helps new users discover what capabilities are available.
diff-explain
Explain a git diff or branch comparison in plain language. Describes the intent behind changes, not just what files were modified. Useful for MR reviews and catching up.