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 skills add littlebearapps/pitchdocs --skill feature-benefitsgit clone --depth 1 https://github.com/littlebearapps/pitchdocsWrote 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/skills/littlebearapps/pitchdocs/feature-benefits)<a href="https://agentmods.dev/skills/littlebearapps/pitchdocs/feature-benefits"><img src="https://agentmods.dev/badge/skills/littlebearapps/pitchdocs/feature-benefits/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/littlebearapps/pitchdocs/feature-benefits"><img src="https://agentmods.dev/badge/skills/littlebearapps/pitchdocs/feature-benefits.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00085 | $0.01477 |
| Opus 5 | $0.00043 | $0.00739 |
| Sonnet 5 | $0.00017 | $0.00295 |
| Haiku 4.5 | $0.00009 | $0.00148 |
Grade A, and why
feature-benefits 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 9d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature-Benefits Extraction
Scan a codebase systematically, extract concrete features with evidence, classify by impact, and translate into benefit-driven language for documentation.
7-Step Feature Extraction Workflow
Step 1: Detect Project Type
Read the primary manifest to understand the ecosystem:
| File | Ecosystem | Key Fields |
|---|---|---|
package.json |
Node.js / JavaScript / TypeScript | dependencies, scripts, bin, exports, type |
pyproject.toml |
Python | [project.dependencies], [project.scripts], [tool.*] |
Cargo.toml |
Rust | [dependencies], [features], [[bin]] |
go.mod |
Go | require, module path |
.claude-plugin/plugin.json |
Claude Code Plugin | skills, commands, agents, hooks |
Also check: Makefile, Dockerfile, docker-compose.yml, .github/workflows/, wrangler.toml for deployment signals.
Step 2: Scan Signal Categories
Scan the 10 signal categories: CLI Commands, Public API, Configuration, Integrations, Performance, Security, TypeScript/DX, Testing, Middleware/Plugins, Documentation.
For each category, check file patterns, read matching files, and record what you find. For detailed file patterns and scan lists per category, load SKILL-signals.md from this skill directory.
Step 3: Extract Concrete Features with Evidence
For each signal found, create a feature entry:
Feature: [What it does — concrete, specific]
Evidence: [File path, function name, or config that proves it]
Category: [Signal category from Step 2]
Rules:
- Every feature must have a file path or function as evidence
- No speculative features — if you can't point to code, it's not a feature
- Be specific: "Zero-config TypeScript support" not "Good developer experience"
Step 3.5: Map to Jobs-to-be-Done (Hero features only)
For Hero features, frame the job: When I am [situation], I want [capability], so I can [outcome]. Classify as Functional, Emotional, or Social. Skip JTBD for Core/Supporting tiers and projects with fewer than 5 features. For full JTBD guidance, load SKILL-signals.md.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 126 lines · 85 tokens per session scan A 1cf1a7308e51
feature-benefits is a skill published in the GitHub repository littlebearapps/pitchdocs (8 stars, last pushed 4mo ago), licensed MIT. It adds 85 tokens to every session and 1,477 once invoked, about $0.0004 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 skills, from other repositories
docs
Generate and update living documentation — tech docs, user guides, philosophy overview. Composable building block for CLOSE and other skills.
init-rpm
Project setup and verification. First run creates rpm context for a project. Repeat runs verify that an existing rpm setup matches the latest expected layout and apply safe migrations.
root-cause-first
A debugging discipline that requires finding the underlying cause of a bug before changing the code. It also sets rules for handling errors, fallbacks, retries, and temporary diagnostics.
refresh
Use when an existing contextualizer's references may have drifted from current upstream state — typically weekly, or whenever a few days of upstream changes have accumulated — to bring them back into agreement.
backlog
Manage the rpm backlog (long-term project tasks in docs/rpm/future/tasks.org — distinct from Claude's native TaskCreate list, which is session-scoped). Add, list, review, postpone, or complete entries. TRIGGER on natural-language backlog operations — phrasings like "backlog X", "add X to backlog", "add to backlog"…
using-skill-engine
When the user mentions skill-engine or "the engine" without naming a specific workflow, or wants first-run setup. Inspects .claude/skills/-context/ install state (and any pending -context.proposed/ proposals) across all three install levels, then dispatches to engine-bootstrap when no contextualizer exists, to…