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 skills/ashaychangwani/imprint/commitnpx skills add ashaychangwani/imprint --skill commitgit clone --depth 1 https://github.com/ashaychangwani/imprintWhat 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 | $0.00020 | $0.00523 |
| Opus 5 | $0.00010 | $0.00262 |
| Sonnet 5 | $0.00004 | $0.00105 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
commit 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Skill
Create a well-formed conventional commit from the currently staged changes.
Step 1 — Check staged changes
Run git diff --cached --stat to see what's staged. If nothing is staged, tell the user and stop.
Run git diff --cached to read the actual diff.
Step 2 — Determine commit type
Pick the type based on the nature of the change:
| Type | When to use |
|---|---|
feat |
New user-facing feature or capability |
fix |
Bug fix |
refactor |
Code restructuring without behavior change |
perf |
Performance improvement |
test |
Adding or updating tests |
docs |
Documentation only |
ci |
CI/CD configuration |
chore |
Maintenance, dependencies, tooling |
build |
Build system or external dependency changes |
style |
Formatting, whitespace, linting (no logic) |
Step 3 — Determine scope
Pick a scope from the file paths changed. Established scopes in this repo:
cli, probe, backend, playbook, stealth-fetch, cron, notify, utils, types, replay-backend, mcp, record, redact, session-writer
If the change spans multiple areas, omit the scope. If it's a new area, derive the scope from the directory name.
Step 4 — Write the commit message
Format: <type>(<scope>): <subject>
Rules:
- Subject line: imperative mood, lowercase, no period, under 72 chars
- Body (optional): explain WHY, not WHAT. Wrap at 100 chars.
- Footer (optional):
BREAKING CHANGE: <description>if applicable
Step 5 — Show and confirm
Show the proposed commit message to the user. Ask if they want to proceed, edit, or cancel.
Step 6 — Execute
Run the commit using a heredoc:
git commit -m "$(cat <<'EOF'
<commit message here>
EOF
)"
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 · 70 lines · 20 tokens per session scan A 32007546c0be
commit is a skill published in the GitHub repository ashaychangwani/imprint (21 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 523 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 2026-08-30.
Other skills, from other repositories
writing-gauntlet-stories
Use when writing or reviewing a Gauntlet story card. Establishes the calibration framing — outcomes, persona binding, observable acceptance criteria — and explicitly rules out wrong-shaped frames (Agile user stories, QA step-scripts, BDD Given/When/Then) so prior knowledge does not contaminate the card.
control-chrome
Control and inspect the user's real Google Chrome through byob's local MCP tools. Use when Claude Code must work with an existing signed-in browser session, open or navigate tabs, understand a rendered page, click or type in web UI, capture screenshots, inspect console or network activity, download page assets, upload…
rust-mcp-server-generator
Generate a complete Rust Model Context Protocol server project with tools, prompts, resources, and tests using the official rmcp SDK.
scraper-recipe
Génère un scraper Bxc complet (profil choisi + extraction typée Zod + sortie JSONL). À utiliser quand l'utilisateur demande "scrape X", "extract Y from URL Z", ou veut un nouveau scraper one-shot dans examples/ ou un sub-package dans packages/.
bxc Core
This skill should be used when the user asks to work on bxc (or similar Bun + Rust FFI native browser/X/Grok/agent engine projects), "bxc stack", "zero-spawn", native X client, Grok xAI high-level, bxc-mcp, scraper packages, rust-bridge FFI, autopilot, CLAUDE.md rules, cross-platform Bun/Rust builds, or needs patterns…
bxc Grok xAI High-Level Client
This skill should be used for anything involving @aphrody/xai (high-level Chat.createChat/append/sample/stream/executeToolCalls/sampleStructured), XTools for native X fulfillment, SuperGrok / OIDC keyless (SUPERGROKTOKEN or /.grok/auth.json), reasoningeffort, structured outputs, tool calling loops with real @aphrody/x…