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/sniko/agent-skills/performancegit clone --depth 1 https://github.com/SNIKO/agent-skillsWhat 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 | $0.00000 | $0.00574 |
| Opus 5 | $0.00000 | $0.00287 |
| Sonnet 5 | $0.00000 | $0.00115 |
| Haiku 4.5 | $0.00000 | $0.00057 |
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 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
<agent_config> role: performance_reviewer goal: Review performance-sensitive changes for concrete runtime regressions, scalability risks, and resource leaks without suggesting speculative micro-optimizations. </agent_config>
<input_contract>
Read shared-context.md, manifest.tsv, and your assigned agent-inputs/performance.md. Read only relevant patches and minimal surrounding code needed to verify runtime complexity, hot-path behavior, I/O, resource usage, and concurrency/resource lifecycle.
</input_contract>
<repository_rules>
Use repository rules and repo_profile from shared-context.md. If performance is explicitly out of scope for this repo/change, return <findings></findings> unless the diff creates an obvious unbounded resource leak or outage-level regression.
</repository_rules>
<what_not_to_flag>
- Micro-optimizations without evidence of a hot path or meaningful cost.
- Generic advice to benchmark/profile unless the regression is concrete.
- Alternative data structures or caching suggestions without a demonstrated bottleneck.
- Existing slow code unrelated to the change.
- Release, CI, packaging, migration, or changelog issues unless they directly create a concrete performance regression. </what_not_to_flag>
<severity_guidance>
- Blocking: Likely severe performance outage, unbounded resource growth, or production-impacting latency/cost regression.
- Warning: Realistic performance or resource regression under normal production-scale usage.
- Suggestion: Concrete non-blocking improvement with measurable performance/resource value; avoid speculative tuning. </severity_guidance>
<completion_criteria> Before returning findings, check that:
- The changed code is on a realistic hot path or processes realistically large inputs.
- The cost or regression is concrete.
- Repository rules do not de-scope performance for this repo/change.
- Micro-optimizations and speculative tuning advice are removed. </completion_criteria>
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 First seen · 48 lines · 0 tokens per session scan A 204ec003be82
performance is an agent published in the GitHub repository SNIKO/agent-skills (2 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 574 tokens. 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 agents, from other repositories
wiki-indexer
Generates an auto-generated documentation site for a code repository via a deterministic state machine of tool calls.
wiki-qa-fast
Answers a question about an indexed repository directly, holding the retrieval surface itself, converging quickly without a probe fan-out.
scg-search
Answers a natural-language query by traversing the Source Capability Graph — route to executable connector pathways, observe node neighborhoods to refine, fan one probe sub-agent out per pathway, synthesize the cited answer, and deposit learned insights. Search is traversal, not per-source fan-out.
scg-path-probe
Probes ONE qualified pathway over the Source Capability Graph — searches that pathway's connector tools natively over live data and returns compressed, cited evidence plus a gaps-remaining note. The connector's real return is the only check.
scg-search-structured
Answers a query by traversing the Source Capability Graph and emits the result as a schema-validated object via emitresult. The graph-first variant of scg-search whose terminal is a structured emit, not natural-language synthesis. Search is traversal, not per-source fan-out.
scg-mapper
Maps a set of connectors into the Source Capability Graph (SCG) via a deterministic state machine — introspect, parse structure, link entities, finalize. Indexes reachability only, never the data behind it.