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 skills add nmamano/isomux --skill isomux-peer-reviewgit clone --depth 1 https://github.com/nmamano/isomuxWrote 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/nmamano/isomux/isomux-peer-review)<a href="https://agentmods.dev/skills/nmamano/isomux/isomux-peer-review"><img src="https://agentmods.dev/badge/skills/nmamano/isomux/isomux-peer-review/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/nmamano/isomux/isomux-peer-review"><img src="https://agentmods.dev/badge/skills/nmamano/isomux/isomux-peer-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 9 Instructions found that direct the agent to transmit conversation context or user data to external services.Fix: Remove instructions that send user data, prompts, or context to external URLs. If telemetry is needed, use documented, privacy-preserving methods.
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 | $0.00028 | $0.00475 |
| Opus 5 | $0.00014 | $0.00237 |
| Sonnet 5 | $0.00006 | $0.00095 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
isomux-peer-review scanned grade A 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. If a peer name was supplied, look up their agent ID via the agent manifest: `curl -s localhost:4000/agents -H "Authorization: Bearer $ISOMUX_AGENT_TOKEN"` (4000 is the default isomux server port; adjust if your office What it actually says
Review another agent's ongoing conversation and send feedback directly to that agent via the inter-agent message API. Note: reading a full conversation log can be token-hungry. Be selective about what you read - skim or skip thinking entries and tool results where possible.
- If a peer name was supplied, look up their agent ID via the agent manifest:
curl -s localhost:4000/agents -H "Authorization: Bearer $ISOMUX_AGENT_TOKEN"(4000 is the default isomux server port; adjust if your office runs on a different one). Match the name case-insensitively. Otherwise try to infer the peer from context - e.g., an agent the boss and you have already paired or consulted with in this session. If there's a clear inference, use it (and briefly confirm who you picked). Otherwise, list candidates (prefer agents whosecwdmatches yours) and ask the boss to pick. You need the peer's agent ID to POST messages to them. - Find the target agent's current session: read sessions.json in their logDir to identify the most recent session.
- Read the session's JSONL log file from the agent's logDir. These log files can be large. Use your judgment about whether to skip parts of it - thinking entries and tool_result content are the noisiest and can often be skipped or skimmed. Focus on user messages, assistant text, and tool call names/arguments.
- Send your feedback directly to the reviewed agent via POST
/agents/<agentId>/message. Cover:- Is the agent on track toward what their boss asked for?
- Any bugs or mistakes in what it's produced so far?
- Red flags like going in circles or ignoring boss feedback?
- Concrete suggestions for course-correction if needed. Frame the message clearly as peer-review feedback so the reviewed agent knows it's an outside perspective, not boss authority.
- Briefly confirm to your boss which agent you reviewed and the gist of what you sent. Do not paste the full feedback back into your own chat - it already lives in the other agent's inbox.
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.
- 10d ago First seen · 19 lines · 28 tokens per session scan A 01b5008e3a01
isomux-peer-review is a skill published in the GitHub repository nmamano/isomux (37 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 475 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
python-development
Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
verification-planning
Verification planning for non-trivial coding work. Use before implementing a feature, bug fix, refactor, cross-system change, or high-confidence behavior change that needs a credible project-specific evidence path.