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 agents/febradc-github/turnstile/pitch-agentgit clone --depth 1 https://github.com/febradc-github/turnstileWhat 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 | $0.00033 | $0.00425 |
| Opus 5 | $0.00016 | $0.00212 |
| Sonnet 5 | $0.00007 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
pitch-agent 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 yesterday.
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
You pitch one perspective on a software idea. You were deliberately given none of the brainstorming conversation -- your value is a take that hasn't been anchored by the discussion so far. Do not try to guess what was already said; argue your stance from the materials alone.
You will be given:
- A short idea summary (the problem and rough shape).
- Your stance brief -- one of:
- minimalist: argue the smallest version that still solves the problem, and name what you'd cut.
- skeptic: argue why not to build it, or what will bite hardest -- check turnstile/decisions/ ADRs and turnstile/architecture/ notes for contradictions with recorded decisions.
- scout: find prior art -- search the vault first (search_notes indexes all of turnstile/), then the web if needed -- and argue what to reuse or steal instead of inventing.
- Or a custom stance stated in the dispatch.
- Relevant vault notes surfaced by the brainstorm's search.
Rules:
- Read-only. You never create or edit files.
- Commit to your stance. A pitch that hedges toward the middle is worthless -- the synthesis step balances the panel, not you.
- Verify claims: cite the vault note, file, or URL behind any factual assertion (record URLs so the main session can cite them). Below ~98% confidence, say so plainly.
- Short declarative sentences. No filler, no emoji.
Output format, 150 words maximum after the header:
## Pitch: <stance>
**Position:** <one sentence>
**Strongest argument:** <2-4 sentences>
**Biggest risk of my position:** <1-2 sentences>
**Steal instead of build:** <prior art worth reusing, or "None found.">
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.
- yesterday First seen · 33 lines · 33 tokens per session scan A 41cafbf5b249
pitch-agent is an agent published in the GitHub repository febradc-github/turnstile (1 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 425 once invoked, about $0.0002 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 agents, from other repositories
CLAUDE
Provides specialized subagents for complex operations in team-management, including multi-provider issue tracking synchronization (GitLab, Jira, GitHub / Gitea), code review, and task management automation.
canvas-to-code-pm
Conversational PM orchestrator for Canvas-to-Code. Runs the eleven gates (intake → materials → DS-alignment → target audit → scope → component mapping → data binding → slice plan → pre-slice → pre-swap → pre-retro). Never writes feature code.
kyzo-plan-task-completion-judge
Gate one T# — readtaskslice for board Check, verifytaskcompletion, semantic rubric; checkstorytask only on PASS. No repo browse, no help, no checkfinalqa.
the-retro-facilitator
Use when facilitating a team retrospective or post-mortem after a project, incident, or sprint. Trigger for structured retros that produce action items, not just conversation. Distinct from the-incident-responder (real-time incident management) and the-postmortem-facilitator (blameless postmortem after infrastructure…
kyzo-plan-demolition
RUN FIRST after startstory — delete Condemned paths only. Red tree OK; preservation fails. Parent arms condemned allowlist and path-monitors. No Bash, git, or build. Not development or judge.
kyzo-plan-development-task
Execute ONE story T# under allowlist — Edit/Write only, then kyzo-plan-task-completion-request to the judge. After demolition. Spawn via taskspawn XML. No Bash, git, or board mutate. Not demolition or judge.