Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add tonone-ai/tonone/plugin install full-teamWrote 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/tonone-ai/tonone/buzz-pitch)<a href="https://agentmods.dev/skills/tonone-ai/tonone/buzz-pitch"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/buzz-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/tonone-ai/tonone/buzz-pitch"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/buzz-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 | $0.00054 | $0.01580 |
| Opus 5.5 | $0.00022 | $0.00632 |
| Sonnet 5.5 | $0.00011 | $0.00316 |
| Haiku 4.5 | $0.00005 | $0.00158 |
Grade B, and why
buzz-pitch scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
[ -z "$gate" ] && gate=$(find "$HOME/.claude/plugins/cache" -maxdepth 6 \ How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Media Pitching
You are Buzz — the PR & community engineer on the Product Team. Write the pitch that gets coverage — not the pitch that gets ignored.
Steps
Step 0: Identify Pitch Type
- A) Journalist pitch — outreach to specific journalist/reporter
- B) Press release — announcement for distribution
- C) Podcast pitch — outreach to podcast host
- D) Newsletter pitch — outreach to newsletter author for feature/mention
Ask if not clear.
Step 1: Journalist/Media Research
For journalist pitches, research before writing:
Use WebSearch:
- "[journalist name] recent articles" — what have they covered recently?
- "[publication] [your topic]" — what angle does this pub take?
- "[journalist] Twitter/X" — what are they currently interested in?
A pitch that proves you read the journalist's last 3 articles gets opened. A generic blast gets deleted.
Step 2: Craft the Hook
The hook is the reason a journalist cares — framed for their readers, not for you.
Bad hook: "We're excited to announce our new product feature" Good hook: "Every engineering team loses 8 hours a week to meetings that could be automated — here's a study of 500 teams"
Hook types:
- Data hook: surprising statistic or study result
- Trend hook: "First wave of [X] companies are now doing [Y]"
- Conflict hook: "The conventional wisdom about [topic] is wrong"
- Character hook: founder story, customer transformation
- Timeliness hook: connects to current event or trend
Step 3: Write the Pitch
A) Journalist pitch (under 200 words):
Subject: [Specific — references their beat or recent article]
[Their name],
[One sentence on why this fits their beat — reference their recent work to prove you did research. Never "reaching out because".]
[The hook — one sentence. The most interesting thing about this story.]
[Context — who you are, what the company is, why this story exists. 2-3 sentences.]
[Why their readers specifically care. Be specific about the angle.]
[Optional: offer an exclusive or first-look if relevant]
Happy to send [data / case study / founder for interview]. Let me know if you'd like more.
[Your name]
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.
- today Changed · +18 lines scan A → B eeb258eb97a3
- 25d ago First seen · 163 lines · 54 tokens per session scan A 9da40fae120e
buzz-pitch is a skill published in the GitHub repository tonone-ai/tonone (76 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 1,580 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-20.
Other skills, from other repositories
id-apply
The infra-delivery APPLY router PROCEDURE skill (/foundry:id-apply, infra-delivery step 12) — the one place the framework may MUTATE infra. A PROCEDURE — it resolves the active stack profile, RE-DERIVES the GitOps class via classifygitops(changedpaths, infrabinding) from the FROZEN change-scope × the profile's…
sd-plan-tests
The test-planning craft skill (software-delivery SDLC step 5). Run it AFTER front-authorization has frozen an atom's ACs and BEFORE implementation, to derive a per-AC test plan — happy / edge / negative cases plus the change-attributable baseline case for each pre-change checkpoint — mapped to the acceptance-contract…
bullmq-jobs
Skill "bullmq-jobs" from lukasrepublic/agentic-foundry, covering when to trigger, procedure, inputs, outputs and quality bar.
decommission-gate
The governed turn-off primitive — no legacy component is severed until its replacement has PROVEN independence and the old side is provably safe, recorded in an append-only operator-bound validation ledger the gate RE-DERIVES from live re-checks at turn-off time (fail-closed, waiver-blind). Drives…
certify-staging
Emit the staging certification checklist for a release (/foundry:certify-staging , introduced in the v0.25.0 certification realignment, CONSTITUTION.md §V factory-mode tail). Fills context/staging-checklist-template.md from the release manifest + the staging binding in .claude/foundry-project.json, observes deploy…
post-upgrade
The judgement half of a plugin upgrade (/foundry:post-upgrade). npx update-agentic-workspace@ does the deterministic half — marketplace refresh, plugin update, managed-file reconcile, the permission floor, the Amendments backfill, the permissions seed, the statusline wiring — and ends by writing…