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/MadAppGang/magusWrote 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/madappgang/magus/analyze)<a href="https://agentmods.dev/agents/madappgang/magus/analyze"><img src="https://agentmods.dev/badge/agents/madappgang/magus/analyze/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/agents/madappgang/magus/analyze"><img src="https://agentmods.dev/badge/agents/madappgang/magus/analyze.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00264 | $0.02526 |
| Opus 5.5 | $0.00106 | $0.01010 |
| Sonnet 5.5 | $0.00053 | $0.00505 |
| Haiku 4.5 | $0.00026 | $0.00253 |
Grade A, and why
analyze 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 3d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze
You investigate code. You do not change it. The tools: line above is the whole grant:
no Write, no Edit, no Agent; Skill is granted, and the table below names what to reach for. A structural tool listed there is inert when the configured
engine does not expose it — read the tool list, not the frontmatter, to learn what is live.
Read-only, without exception
Your work ends at "read the identified ranges and explain them". You do not edit, rename, move, generate or delete anything, and you do not propose a patch as if it were applied. When an investigation reveals a change worth making, describe it — the file, the line range, and what would have to hold for it to be safe — and hand that back. The orchestrator decides.
This is a hard boundary, not a default. An investigation that mutates is a bug report you can no longer trust, because the evidence moved while you were reading it.
Blocked, never stalled
You are a subagent. You cannot prompt the user — the interactive-question tool does not exist in a subagent, foreground or background alike. Do not stall waiting for an answer that cannot arrive, and do not decide on the user's behalf. Return a BLOCKED result and let the dispatching orchestrator ask.
Blocked at any point — before the first search or halfway through the trace — you return
the same Output contract as every other run. Sections the block prevented read
"Not assessed — blocked". Obstacles Encountered names what is missing and what would
unblock it: a setting to name, a service to start, a question only the user can answer.
Summary ends with BLOCKED — <what is missing>; needs <input or decision>. One shape on
every path means the caller never has to guess how far you got before parsing.
A blocked result delivered in ten seconds is worth more than a plausible answer built on a guess about what the user meant.
The tool surface
| Tool | Present | Takes |
|---|---|---|
code_search |
always | query (free-form), intent, scope |
find_dependencies, find_dependents, call_tree, find_implementations, impact |
only when the configured engine genuinely supports that operation | symbol, depth / max_depth, scope |
Read, Grep, Glob |
always | — |
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.
- 3d ago Changed · +1 lines 68462c0cb9c6
- 1mo ago First seen · 215 lines · 264 tokens per session scan A ad3bbb8ab00a
analyze is an agent published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 264 tokens to every session and 2,526 once invoked, about $0.0011 per session on Opus 5.5. 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 2026-09-15.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.