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/blpsoares/agentistics/update-docsgit clone --depth 1 https://github.com/blpsoares/agentisticsWhat 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 | $0.00481 |
| Opus 5 | $0.00000 | $0.00241 |
| Sonnet 5 | $0.00000 | $0.00096 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
update-docs 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 today.
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
/update-docs
Update all documentation in this project to reflect the current state of the codebase.
What to do
- Read every markdown file listed below
- Read the actual source files they reference to verify what's still true
- Rewrite only what's outdated — preserve accurate content and existing structure
- Run
bun tsc --noEmitat the end to confirm nothing broke
Files to update (in priority order)
| File | Covers |
|---|---|
CLAUDE.md |
Developer instructions for AI assistants — most critical |
README.md |
Project overview, features, install steps |
docs/architecture.md |
System architecture and data flow |
docs/data-sources.md |
Data sources and processing logic |
docs/metrics.md |
Metrics tracked and how they're calculated |
docs/mcp.md |
MCP server tools and usage |
docs/nay.md |
Nay agent documentation |
docs/opentelemetry.md |
OpenTelemetry export |
packages/mcp/README.md |
MCP package standalone readme |
Key things to check
- Monorepo structure: does the doc list all packages (
core,server,web,mcp,desktop)? - Calculation functions: are
calcCost,getModelPrice,MODEL_PRICINGcorrectly attributed to@agentistics/core? files_modified: is it documented that this now counts Edit/Write/MultiEdit tool calls (not just git)?git.tsworkspace fallback: documented that non-git project dirs scan subdirs?- PWA: mentioned in features/architecture?
- Settings modal: unified tabbed modal (Preferences / Live / Install / Environment)?
- Chat sounds:
chatSounds.tswith 5 synthesized tones? - MCP tools: all 11 tools listed and accurately described?
Rules
- CLAUDE.md must be kept precise — it's read by AI assistants on every session
- Don't add content that isn't true yet (e.g. desktop app is in-progress, not shipped)
- Don't change tone or add emojis
- When in doubt about whether something changed, read the source file
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.
- today First seen · 43 lines · 0 tokens per session scan A 513fb9609a25
update-docs is a command published in the GitHub repository blpsoares/agentistics (39 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 481 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 2026-09-01.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
design-review
Workflow recipe — review a design end-to-end, ending in measured numbers rather than adjectives, by chaining 4 skills.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
security-review
CWE 기반 보안 검토 + STRIDE 위협 모델링 (v6 - effort:max 강제).
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
release-harn
Run the tag-first Harn release workflow.