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/littlebearapps/pitchdocs/featuresgit clone --depth 1 https://github.com/littlebearapps/pitchdocsWhat 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 | $0.00013 | $0.00770 |
| Opus 5 | $0.00006 | $0.00385 |
| Sonnet 5 | $0.00003 | $0.00154 |
| Haiku 4.5 | $0.00001 | $0.00077 |
Grade A, and why
features 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/features
Scan a codebase, extract its features with evidence, and translate them into benefit-driven language.
Behaviour
- Load the
feature-benefitsskill and run the 7-step Feature Extraction Workflow - If GitHub MCP tools are unavailable (GitLab/Bitbucket), gather equivalent data via
glabCLI, REST API, or git history - Follow the auto-loaded
doc-standardsrule for tone and benefit translation
Arguments
- No arguments: Full extraction — outputs a structured feature inventory to chat with Hero, Core, and Supporting tiers
table: Outputs a ready-to-paste| Feature | Benefit | Status |markdown table suitable for a READMEbullets: Outputs emoji+bold+em-dash bullets (- 🔍 **Feature** — benefit) — more scannable for 5+ featuresbenefits: Runs persona inference + user benefits synthesis (Steps 3.6 and 4). Offers a choice of auto-scan or conversational ("talk it out") path. Outputs bold-outcome bullets for use in a "Why [Project]?" sectionaudit: Compares extracted features against the existing README features section, reports undocumented and over-documented features
Output Formats
Default (Inventory)
Feature Inventory: [project-name]
Hero Features (1–3)
1. [Feature] — [Evidence file] — [Benefit category]
Benefit: [Translated benefit sentence]
Core Features (4–8)
2. [Feature] — [Evidence file] — [Benefit category]
Benefit: [Translated benefit sentence]
...
Supporting Features
9. [Feature] — [Evidence file] — [Benefit category]
...
Table Mode
| Feature | Benefit | Status |
|---------|---------|--------|
| [Hero feature] | [Benefit sentence] | :white_check_mark: Stable |
| [Core feature] | [Benefit sentence] | :white_check_mark: Stable |
| [Core feature] | [Benefit sentence] | :construction: Beta |
Bullets Mode
- **[Hero feature]** — [Benefit sentence with evidence]
- **[Core feature]** — [Benefit sentence with evidence]
- **[Core feature]** — [Benefit sentence with evidence]
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 · 95 lines · 13 tokens per session scan A 7a14afffda47
features is a command published in the GitHub repository littlebearapps/pitchdocs (7 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 770 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
create-skill
Create an AI skill from any source (URL, repo, PDF, video, notebook, etc.).
install-skill
One-command skill creation and packaging for a target platform.
sync-config
Sync a scraping config's URLs against the live documentation site.
review-renovate
Review and merge renovate PRs with automerge configuration updates.
monitor-ci
Monitors pull request CI checks until they are resolved (pass or fail).
/add-claude-rule
Appends the rule from $ARGUMENTS to CLAUDE.md.