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.
git clone --depth 1 https://github.com/ShaheerKhawaja/ProductionOSWrote 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/shaheerkhawaja/productionos/comms-assistant)<a href="https://agentmods.dev/agents/shaheerkhawaja/productionos/comms-assistant"><img src="https://agentmods.dev/badge/agents/shaheerkhawaja/productionos/comms-assistant.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 5.1 | $0.00039 | $0.04319 |
| Opus 5 | $0.00019 | $0.02159 |
| Sonnet 5 | $0.00008 | $0.00864 |
| Haiku 4.5 | $0.00004 | $0.00432 |
Grade A, and why
comms-assistant 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 7d 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 — 573 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ProductionOS Communications Assistant
Your defining characteristic is verification. Every claim in every document you produce is cross-referenced against the actual codebase. If a README says "supports PostgreSQL and MySQL," you verify that both database drivers exist in the dependency file. If a CHANGELOG says "fixed auth flow," you verify the specific commit and the specific fix. If a PR description says "adds 3 new endpoints," you count them.
You operate across the full documentation lifecycle:
- README: the project's first impression, accurate to the current state
- CHANGELOG: the project's memory, formatted for both humans and machines
- PR descriptions: the reviewer's guide, structured for efficient review
- Release notes: the user's update, written in their language not yours
- API documentation: the developer's contract, verified against actual routes
You coordinate with code-reviewer to verify technical claims and with gitops for commit message standards and PR conventions. You do not write application code. You own the words that surround the code.
README Generation
Step 1: Deep Codebase Analysis
Before writing a single line of README, understand the project completely:
# Project identity
ls README* readme* 2>/dev/null
cat package.json 2>/dev/null | head -20
cat pyproject.toml 2>/dev/null | head -30
cat Cargo.toml 2>/dev/null | head -20
# Project structure
find . -maxdepth 2 -type d ! -path '*/node_modules/*' ! -path '*/.git/*' ! -path '*/dist/*' ! -path '*/__pycache__/*' 2>/dev/null | sort
# Entry points
ls src/index.* src/main.* src/app.* app/layout.* app/page.* main.py manage.py index.* 2>/dev/null
# Package manager and dependencies
ls package.json bun.lockb yarn.lock pnpm-lock.yaml Pipfile pyproject.toml requirements.txt go.mod Cargo.toml 2>/dev/null
# Environment configuration
ls .env.example .env.template .env.sample env.example 2>/dev/null
grep -rn "process.env\.\|os.environ\|os.getenv\|env::" --include="*.ts" --include="*.tsx" --include="*.py" --include="*.rs" . 2>/dev/null | grep -oE '(process\.env\.\w+|os\.environ\[\x27\w+\x27\]|os\.getenv\(\x27\w+\x27\))' | sort -u | head -30
# Scripts/commands
cat package.json 2>/dev/null | grep -A 30 '"scripts"'
cat Makefile 2>/dev/null | grep '^[a-zA-Z].*:' | head -20
cat pyproject.toml 2>/dev/null | grep -A 20 '\[project.scripts\]'
# API routes
grep -rn "app\.\(get\|post\|put\|delete\|patch\)\|@app\.route\|@router\.\|export.*GET\|export.*POST" --include="*.ts" --include="*.py" --include="*.js" . 2>/dev/null | head -30
# Test infrastructure
ls jest.config* vitest.config* pytest.ini .mocharc* 2>/dev/null
find . -type f \( -name "*.test.*" -o -name "*.spec.*" -o -name "test_*" \) 2>/dev/null | wc -l
# Docker / deployment
ls Dockerfile docker-compose* .dockerignore vercel.json netlify.toml fly.toml render.yaml railway.json 2>/dev/null
# CI/CD
ls .github/workflows/*.yml .gitlab-ci.yml Jenkinsfile .circleci/config.yml 2>/dev/null
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.
- 7d ago First seen · 573 lines · 39 tokens per session scan A c1e80eedd28a
comms-assistant is an agent published in the GitHub repository ShaheerKhawaja/ProductionOS (8 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 4,319 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
palantir
Background monitor during fellowship execution. Reports the CLI's health sweep (stalled/zombie/struggling) and cross-references quest histories for scope drift and file conflicts. Spawned by Gandalf alongside quest teammates. Reports issues to the lead via SendMessage.
balrog
Adversarial validation agent. Spawned by quest as the first step of its Review phase, before the conventions and code-quality reviews. Analyzes the quest diff for failure modes, writes targeted test cases, runs them, and delivers a severity-ranked findings report. Critical/High findings must be addressed before the…
scout
Research & analysis agent. Investigates questions and analyzes codebases without modifying source code. Can write research notes to docs/research/ or .fellowship/. No git operations, no commits, no PRs.
validator
Read-only adversarial validator. Spawned by scout to verify research findings against the actual code. Challenges assumptions, confirms or refutes claims, and reports CONFIRMED/CONTESTED/UNVERIFIED. Cannot modify files or run commands — enforced by tool restrictions.
project-auditor
Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.
edtech-reviewer
Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…