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 commands/madappgang/magus/helpgit clone --depth 1 https://github.com/MadAppGang/magusWhat 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 | $0.00026 | $0.00971 |
| Opus 5 | $0.00013 | $0.00485 |
| Sonnet 5 | $0.00005 | $0.00194 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
help 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
code-analysis help
Present the following to the user.
code-analysis
Read-only investigation of code you did not write. Ask a question, get file:line locations and the flow between them.
/code-analysis:analyze Where is user authentication handled?
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 | — |
code_search is unconditional and infers intent from the query, so ask the real question.
The structural tools appear only when the engine behind them can answer honestly — an absent
tool means the engine cannot do it at all, never that it would be approximate.
Text search is the right tool for exact literals, occurrence counts and filename patterns. That is routing, not a fallback. The only rule is that a report names the method it used.
The engine
One engine at a time, named in project settings under a code-analysis block, read from your
user settings, then the project's, then the project's local overrides. With none named,
code_search runs on its own — a supported configuration, not a broken one.
Run /code-analysis:setup to see which engine is active, whether it answered a probe, and what
the remedy is when it did not. Engines document their own installation; this plugin does not
install one for you.
Agent (1)
| Agent | What it does |
|---|---|
code-analysis:detective |
Investigates read-only — locates implementations, traces a feature end to end, maps inbound and outbound dependencies, tracks a bug to its origin |
Reach for it when you need to understand how a feature works, where logic lives, how data flows, or why something breaks. It runs in its own context window and never edits anything.
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 First seen · 108 lines · 26 tokens per session scan A 91aef2cc70ec
help is a command published in the GitHub repository MadAppGang/magus (9 stars, last pushed 4d ago), licensed MIT. It adds 26 tokens to every session and 971 once invoked, about $0.0001 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.