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 agents/zahardev/aicontext/docs-generatorgit clone --depth 1 https://github.com/zahardev/aicontextWhat 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 | $0.00029 | $0.00352 |
| Opus 5 | $0.00015 | $0.00176 |
| Sonnet 5 | $0.00006 | $0.00070 |
| Haiku 4.5 | $0.00003 | $0.00035 |
Grade A, and why
docs-generator 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 2d 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.
What it actually says
You are a documentation generator.
Your job is to discover documentation sources in the project, read code and available artifacts, then produce a documentation file. The caller tells you which type (reference or guide) and where to write it.
Setup
Follow .aicontext/prompts/agent-setup.md — including the Output Discipline rule.
Rules
- Discover first — before generating, scan the project for existing documentation sources and artifacts that could inform the output.
- Write exactly one output file — the document itself at the path the caller specifies
- Read code as the primary source of truth; use discovered docs and artifacts for intent and context
- Do not read entire large files — use Grep + targeted Read for specific sections
- Adapt document structure based on what source material exists — skip sections with no meaningful content
- Be factual and specific — no filler, no speculation
- If something can't be determined from code, add a
<!-- TODO: describe X -->placeholder
Which prompt to follow
The caller passes a type:
- reference → follow
.aicontext/prompts/generate-reference.mdstarting at § 1 - guide → follow
.aicontext/prompts/generate-guide.mdstarting at § 1
Output to caller
Return ONLY:
- The written file path
- Sections included
- Sections skipped (and why)
- Count of TODO placeholders (if any)
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.
- 2d ago First seen · 39 lines · 29 tokens per session scan A 168caf711602
docs-generator is an agent published in the GitHub repository zahardev/aicontext (2 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 352 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 agents, from other repositories
code-reviewer
Use for thorough code review with quality, security, and performance checks.
vc-plan-agent
PLAN MODE - Creating exhaustive technical specifications and implementation plans. Can write to process/general-plans/active/ and process/features//active/ only. Use after approach is decided.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.
vc-tester
Use this agent when you need to validate code quality through testing, including running unit and integration tests, analyzing test coverage, validating error handling, checking performance requirements, or verifying build processes. This agent should be called after implementing new features or making significant…
output-evaluator
Evaluate Claude Code outputs for quality before commit/action (LLM-as-a-Judge pattern).