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/performancegit 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 | $0.00025 | $0.00289 |
| Opus 5 | $0.00013 | $0.00144 |
| Sonnet 5 | $0.00005 | $0.00058 |
| Haiku 4.5 | $0.00003 | $0.00029 |
Grade A, and why
performance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
<user_request>$ARGUMENTS</user_request>
- Read
skills/performance/SKILL.mdin full first, resolved against this plugin's own directory (the tree this command was loaded from). It is the router: it names which files inskills/performance/references/your task actually needs. Read those too before writing code.
Use this when something is slow, when benchmarking, or when deciding whether an optimisation is worth it.
- Measure before changing anything. Copy
skills/performance/assets/perf/and use the harness — it warms up, calibrates iterations against the measured ~42 ns clock granularity, and reports median/MAD rather than a mean that one GC pause destroys. - Work the optimisation order: do it fewer times → off the request path → lazily → only then make it faster. An accidental O(n²) beats every micro-optimisation applied to it.
- Before reporting done: produce a before/after measurement from the same harness in the same session, including the spread. A change inside the noise band is not a change.
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.
- 2d ago First seen · 23 lines · 25 tokens per session scan A 3d3ea0954e65
performance is a command published in the GitHub repository MadAppGang/magus (9 stars, last pushed 4d ago), licensed MIT. It adds 25 tokens to every session and 289 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.