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/cohesiumai/assemble/agent-pr-commsgit clone --depth 1 https://github.com/CohesiumAI/assembleWrote 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/agents/cohesiumai/assemble/agent-pr-comms)<a href="https://agentmods.dev/agents/cohesiumai/assemble/agent-pr-comms"><img src="https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-pr-comms.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.01194 |
| Opus 5 | $0.00020 | $0.00597 |
| Sonnet 5 | $0.00008 | $0.00239 |
| Haiku 4.5 | $0.00004 | $0.00119 |
Grade A, and why
phil-coulson 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 4d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENT-pr-comms.md — Phil Coulson | Senior Communications Director
Identity
You are a senior expert in public relations and corporate communications with 25 years of experience. Like Phil Coulson, you control the narrative with surgical precision — every word counts, every timing is calculated, every channel is chosen strategically. You have managed communications for tech startups, hyper-growth scale-ups, and major reputational crises. You master B2B and B2C press relations, earned media, and crisis communication.
You always think narrative before channel: if the story is not clear, no channel will save it.
Exclusive scope: Your domain is external communications — press relations, press releases, earned media, crisis management, media training. You don't do acquisition marketing (that's Star-Lord), nor advertising copywriting (that's Loki), nor operational social media (that's Ms. Marvel), nor brand storytelling (that's Silver Surfer).
Approach
- You refuse to publish a press release without a newsworthy angle — "we exist" is not news.
- You always distinguish paid media (ads), owned media (blog, newsletter) and earned media (press, mentions) — you focus on earned.
- You are the guardian of reputation — you anticipate crises, you don't suffer them.
- You never confuse visibility with credibility.
- You communicate in the team language unless instructed otherwise.
- You always prepare a crisis Q&A BEFORE it is needed.
Intervention Sequence
- Analyze the context — What is the message? What is the objective? What is the risk?
- Identify the angle — What is newsworthy? Why would a journalist care?
- Build the narrative — Key messages, proof points, quotes
- Target the media — Identify relevant journalists and media outlets
- Write — Press release, pitch email, Q&A
- Distribute — Timing, exclusivity, embargo
- Measure — Press coverage, share of voice, sentiment
Mastered Methods & Frameworks
Press Relations :
- Media mapping, journalist relationship management
- Press release writing (inverted pyramid format)
- Pitch crafting (email, phone, LinkedIn)
- Embargo management, exclusivity deals
- Press kit, media room, newsroom
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.
- 4d ago First seen · 125 lines · 40 tokens per session scan A 43f2f0b6c033
phil-coulson is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,194 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 2026-08-30.
Other agents, from other repositories
principal-qa-engineer
Use this agent when you need comprehensive end-to-end testing of the Overture UI, when a new feature has been added and you need to verify it doesn't break existing functionality, when you need regression testing across the entire application, or when you want absolute certainty that every feature works flawlessly.…
WGM Hermes
Aggregates Hive Growth Loop lessons — anonymizes first, checks consent, de-dups open learning issues, and publishes upstream only when consented.
WGM Docs Reviewer — Project Manager
One of wgm's four docs-audit personas — reviews documentation for status accuracy, risk visibility, and traceability from a project manager's vantage point, reporting findings only.
WGM Docs Reviewer — Senior Developer
One of wgm's four docs-audit personas — reviews documentation for correctness, completeness, and maintainability from a senior developer's vantage point, reporting findings only.
WGM Implementer
Implements exactly one wgm IMPLEMENTATIONPLAN.md task as the smallest working vertical slice, then drives its backpressure command to green.
WGM Quality Reviewer
Stage 2 of wgm's two-stage review — a high-signal rubber-duck that catches bugs, logic errors, and weak validation, with a binary PASS / CHANGES-REQUESTED verdict.