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 GiustoPiedimonte/agentic-engineering-marketplace --skill pitchgit clone --depth 1 https://github.com/GiustoPiedimonte/agentic-engineering-marketplaceWrote 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/giustopiedimonte/agentic-engineering-marketplace/pitch)<a href="https://agentmods.dev/skills/giustopiedimonte/agentic-engineering-marketplace/pitch"><img src="https://agentmods.dev/badge/skills/giustopiedimonte/agentic-engineering-marketplace/pitch/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/giustopiedimonte/agentic-engineering-marketplace/pitch"><img src="https://agentmods.dev/badge/skills/giustopiedimonte/agentic-engineering-marketplace/pitch.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 | $0.00072 | $0.00696 |
| Opus 5 | $0.00036 | $0.00348 |
| Sonnet 5 | $0.00014 | $0.00139 |
| Haiku 4.5 | $0.00007 | $0.00070 |
Grade A, and why
pitch 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 11d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pitch — shape the spec before the code
A pitch is the source of truth for a piece of work: it captures the problem, the appetite, the shaped solution, and the boundaries. Code is downstream. Never go prompt -> code for non-trivial work; shape first.
$ARGUMENTS is a short description of the feature/problem.
Process
-
Interview the user with the
AskUserQuestiontool. Skip obvious questions; dig into the hard parts they may not have considered:- The problem: what's broken / missing, for whom, why now.
- Appetite: how much time/effort this is worth (this bounds the solution).
- The shape of the solution at a high level (not implementation detail).
- Explicit out-of-scope and hard no-gos.
- Rabbit holes: the risky unknowns, and how to de-risk them.
- "Done-when": the concrete checklist that closes the work. Ask in short rounds. One question at a time when possible.
-
Ground it in the codebase (read-only). Delegate wide reading to the
researchersubagent so the main context stays clean. Inventory what already exists ("substrate already present") so the pitch builds on it, not over it. -
Name the graph. State which of the five graphs this work touches (execution / memory / audit / capability / coordination — usually one primary) and which edges cross a human gate or an irreversible action (the severity×reversibility calls). If the work is a fan-out / audit / review / research job, sketch the nodes and edges — see the
graphskill'sGRAPH_MODEL.md. This makes the gate question explicit before any code, not after. -
Write the pitch to
docs/pitches/<slug>.mdusing the structure inreferences/PITCH_TEMPLATE.md(including theGraphandGated edgesfields). The pitch must be self-contained: name the files/interfaces involved, state what's out of scope, and end with a "Done-when" checklist that includes an end-to-end verification. -
Stop for review. Show the pitch, ask for gaps/corrections. Do not start planning or coding until the user approves. Fix the shape, not the code.
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.
- 11d ago First seen · 58 lines · 72 tokens per session scan A e6da84df15f7
pitch is a skill published in the GitHub repository GiustoPiedimonte/agentic-engineering-marketplace (13 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 696 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 2026-08-30.
Other skills, from other repositories
grill-me
Internal requirements-interview engine for the CCF commands plan and init. Invoked only by those commands through the Skill tool with a mode argument (plan / init); it interrogates the user one question at a time, exploring the code to self-answer first, and returns a summary of the decisions. Not a standalone…
adr-new
Create a new Architecture Decision Record with append-only, status-gated supersession, and update the ADR index. Invoke with /adr-new, or let /tdd-author invoke it on approval of an ADR action (this skill stays model-invocable for that reason).
cco-tools
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.
test-run
Run plugin test suites in this monorepo and report a concise pass/fail summary. Optional plugin slug arg; without arg, runs all plugins under plugins/.
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
design-system-reference
Style guides and implementation rules for frontend design. Works with design-discovery agent which handles context gathering and VS-based style recommendations. Contains detailed style guides, anti-patterns, and implementation checklists.