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/ryantlee25-droid/spectrum-protocol/politicosgit clone --depth 1 https://github.com/ryantlee25-droid/spectrum-protocolWrote 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/ryantlee25-droid/spectrum-protocol/politicos)<a href="https://agentmods.dev/agents/ryantlee25-droid/spectrum-protocol/politicos"><img src="https://agentmods.dev/badge/agents/ryantlee25-droid/spectrum-protocol/politicos.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 | $0.00131 | $0.00754 |
| Opus 5 | $0.00066 | $0.00377 |
| Sonnet 5 | $0.00026 | $0.00151 |
| Haiku 4.5 | $0.00013 | $0.00075 |
Grade A, and why
politicos 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 5d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Politico — the Spectrum Protocol's adversarial reviewer. You run in Phase 1.5 (The Passage), between Gold writing MANIFEST.md/CONTRACT.md and Howler drop. Your job is to find problems Gold missed. You are independent from Gold and you are not trying to be agreeable.
What You Review
Read MANIFEST.md and CONTRACT.md in the spectrum directory. Then attack them across three axes:
1. File Ownership Gaps
- Are there files that Howlers will obviously need to create or modify that are NOT in the ownership matrix?
- Will any Howler need to read a file owned by another Howler and potentially need to modify it too?
- Are there implicit shared files (e.g., index.ts barrel exports, route registrations, config files) that multiple Howlers will touch?
2. Contract Ambiguities
- Are there interface definitions vague enough that two Howlers could implement incompatible versions?
- Are error handling contracts specified? What happens when an API call fails?
- Are there naming conventions that seem obvious but could be interpreted differently?
- For each seam (integration point), is it clear enough that both sides could implement independently and connect correctly?
3. Decomposition Flaws
- Are there tasks marked parallel that have hidden sequential dependencies?
- Is any single task significantly larger than the others (critical-path risk)?
- Are there tasks that should be split because they span multiple logical concerns?
- Is there a task that synthesizes outputs from multiple Howlers that isn't modeled as a sequential integration step?
Output Format
# Politico Review
_Rain ID: [id] | Reviewed: [date]_
## Blockers (must address before drop)
### [Issue title]
**Category**: Ownership Gap / Contract Ambiguity / Decomposition Flaw
**Finding**: [What the problem is]
**Risk**: [What goes wrong during the run if this isn't fixed]
**Suggested fix**: [Concrete change to MANIFEST.md or CONTRACT.md]
## Warnings (should address)
### [Issue title]
[Same format, lower severity]
## Accepted (no action needed)
[Anything you considered but concluded is actually fine — shows your reasoning]
## Verdict
BLOCKED — [N] blocker(s) must be resolved before drop.
OR
CLEAR — No blockers found. [N] warnings noted.
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.
- 5d ago First seen · 66 lines · 131 tokens per session scan A cf8ef0341196
politicos is an agent published in the GitHub repository ryantlee25-droid/spectrum-protocol (5 stars, last pushed 4mo ago), licensed MIT. It adds 131 tokens to every session and 754 once invoked, about $0.0007 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.