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/btspoony/mstar-harness/code-reviewergit clone --depth 1 https://github.com/btspoony/mstar-harnessWrote 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/btspoony/mstar-harness/code-reviewer)<a href="https://agentmods.dev/agents/btspoony/mstar-harness/code-reviewer"><img src="https://agentmods.dev/badge/agents/btspoony/mstar-harness/code-reviewer.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 | $0.00040 | $0.00909 |
| Opus 5 | $0.00020 | $0.00454 |
| Sonnet 5 | $0.00008 | $0.00182 |
| Haiku 4.5 | $0.00004 | $0.00091 |
Grade A, and why
code-reviewer 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 yesterday.
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.
What it actually says
Morning Star Role Binding
You are code-reviewer. The complete role prompt is provided by the mstar-roles skill.
- Skill:
mstar-rolesskill - Role reference:
references/code-reviewer.mdin themstar-rolesskill - Role parameters:
role_id=code-reviewer,mode=subagent
Mandatory First Steps
This file is a routing shell — NOT your complete role prompt. Before any work, load in order:
skill→mstar-harness-core(state machine, gates, routing — global SSOT)skill→mstar-roles(role mapping & parameter table)Read→references/code-reviewer.mdlisted above
System reminders like "ALREADY LOADED" refer to prior sessions — you MUST load these for THIS session.
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.
- yesterday Changed · -2 lines · -42 tokens per session 6f2f51a70163
- 5d ago First seen · 91 lines · 82 tokens per session scan A 0d292b5e9506
code-reviewer is an agent published in the GitHub repository btspoony/mstar-harness (58 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 909 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
qa-agent
The orchestrator (/ship) passes a MODE flag and the corresponding feature root.
backend-agent
MODE and SPECDIR are passed by the orchestrator.
entity-scaffold-agent
Turn DB schema JSON + stack into persistence-layer skeleton only (entities, DbContext, schema.prisma append, etc.). No HTTP layer, no src/features/ product code, no task files.
frontend-agent
The orchestrator (/ship) passes the absolute task file path (and a MODE flag) when invoking this agent.
doc-gen-agent
The orchestrator (/ship) passes a MODE flag determining where to read inputs.
specification-agent
This agent runs in one of two modes, determined by the orchestrator command (/plan).