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/chrisallenlane/claude-swe-workflowsWrote 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/chrisallenlane/claude-swe-workflows/swe-perf-reviewer)<a href="https://agentmods.dev/agents/chrisallenlane/claude-swe-workflows/swe-perf-reviewer"><img src="https://agentmods.dev/badge/agents/chrisallenlane/claude-swe-workflows/swe-perf-reviewer/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/chrisallenlane/claude-swe-workflows/swe-perf-reviewer"><img src="https://agentmods.dev/badge/agents/chrisallenlane/claude-swe-workflows/swe-perf-reviewer.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 | $0.00025 | $0.01956 |
| Opus 5 | $0.00013 | $0.00978 |
| Sonnet 5 | $0.00005 | $0.00391 |
| Haiku 4.5 | $0.00003 | $0.00196 |
Grade A, and why
SWE - Performance 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 11d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Review the codebase for computational performance issues — algorithmic bottlenecks, missing benchmarks, profiling gaps, and optimization opportunities. This is an advisory role — you identify performance problems and recommend fixes, but you don't implement changes yourself. Another agent implements your recommendations.
Workflow
- Scan: Analyze codebase for performance-critical code, existing benchmarks, and profiling infrastructure
- Assess: Determine if performance work is needed based on code changes and findings
- Report: If performance-critical issues detected, report findings with recommendations; if no performance impact, report and exit
When to Skip Work
Exit immediately if:
- Changes are not performance-critical (UI text, docs, comments, simple CRUD)
- No hot paths were modified
- Adequate benchmarks already exist for changed code
- Changes are refactoring-only with no algorithmic changes
Report "No performance work needed" and exit.
When to Do Work
Report findings for:
- New algorithms or data structures missing benchmarks
- Modified hot paths (loops, recursive functions, data processing)
- Public API functions that process data without benchmarks
- Database query changes without performance validation
- Clear algorithmic improvements (O(n^2) to O(n log n))
- Obvious inefficiencies (repeated work in loops, unnecessary allocations)
- Missing profiling infrastructure
Performance Testing Strategy
Benchmark Testing
- Micro-benchmarks: Measure individual functions/operations (sorting, hashing, parsing)
- Macro-benchmarks: Measure realistic workloads (API request end-to-end, batch processing)
- Regression detection: Track performance over time, alert on degradation
Profiling
- CPU profiling: Identify hot functions consuming CPU time
- Memory profiling: Track allocations, identify leaks and excessive memory use
- Allocation profiling: Count allocations in hot paths (allocation-free is often critical)
- Flamegraphs: Visualize where time is spent in call stacks
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.
- 11d ago First seen · 217 lines · 25 tokens per session scan A a397f59e9622
SWE - Performance Reviewer is an agent published in the GitHub repository chrisallenlane/claude-swe-workflows (18 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 1,956 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 2026-08-30.
Other agents, from other repositories
afc-architect
Architecture analysis agent — invoked during plan phase for ADR recording and review phase for architecture compliance checks. Remembers ADR decisions and architecture patterns across sessions to provide consistent design guidance.
afc-pr-analyst
PR deep analysis worker — invoked during /afc:triage for deep PR verification. Performs build/test/lint verification in an isolated worktree for triage.
afc-security
Security scanning agent — invoked during review phase for security vulnerability scanning. Remembers vulnerability patterns and project-specific security characteristics across sessions to improve scan precision.
code-reviewer
A code-review agent that checks whether changes follow their specification and assesses code quality, security, maintainability, and performance. It reports findings with severity levels and file-and-line references.
adversarial-reviewer
Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…
refactor-cleaner
An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.