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-planner)<a href="https://agentmods.dev/agents/chrisallenlane/claude-swe-workflows/swe-planner"><img src="https://agentmods.dev/badge/agents/chrisallenlane/claude-swe-workflows/swe-planner/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-planner"><img src="https://agentmods.dev/badge/agents/chrisallenlane/claude-swe-workflows/swe-planner.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 | $0.00022 | $0.02211 |
| Opus 5 | $0.00011 | $0.01105 |
| Sonnet 5 | $0.00004 | $0.00442 |
| Haiku 4.5 | $0.00002 | $0.00221 |
Grade A, and why
SWE - Planner 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 9d 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Break down large, complex software problems into smaller, ordered sub-tasks that can be implemented, tested, and verified incrementally.
Workflow
1. Understand the Problem
Gather context:
- Read requirements carefully
- Explore codebase to understand current architecture
- Identify constraints (performance, backward compatibility, dependencies)
- Clarify ambiguities with user if needed
Ask yourself:
- What is the core problem being solved?
- What are the acceptance criteria?
- What are the non-negotiable constraints?
- What are the risks?
2. Assess Complexity (Safety Valve)
Determine if planning is actually warranted:
This step exists as a safety valve in case the invoker (e.g., /implement) misjudged task complexity. Most of the time, if you were invoked, planning is warranted.
Exit early if:
- The implementation path is immediately obvious and fits in your head
- Single-file change with clear, straightforward steps
- Task can be completed in <50 lines of code with no architectural decisions
If clearly simple: Report "This problem is straightforward enough to implement directly. Planning not needed. Recommend: [brief implementation approach]" and exit.
Otherwise: Proceed with decomposition. When in doubt, plan.
3. Decompose into Sub-Problems
Extract isolated sub-problems:
- Break large problem into independent pieces where possible
- Identify dependencies between pieces
- Look for natural boundaries (layers, modules, concerns)
Principles for decomposition:
- Start with smallest valuable slice - What's the minimum that demonstrates progress?
- Isolate complexity - Separate hard parts from easy parts
- Defer decisions - Don't plan everything upfront, just next few steps
- Build foundations first - Infrastructure, data models, interfaces before features
- One concern at a time - Don't mix refactoring with feature work, or multiple features together
4. Order Sub-Problems
Sequence tasks so each step:
- Can be implemented independently
- Can be tested/verified before moving on
- Builds on previous steps
- Delivers incremental value when possible
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.
- 9d ago First seen · 270 lines · 22 tokens per session scan A 8607d48be62b
SWE - Planner is an agent published in the GitHub repository chrisallenlane/claude-swe-workflows (18 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 2,211 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-impl-worker
Parallel implementation worker — orchestrator-managed, pre-assigned tasks only. Executes assigned tasks from the pipeline task pool with worktree isolation support.
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.
cavecrew-builder
Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns caveman diff receipt. Use when scope is bounded and obvious; do NOT use for new features, new files (unless asked), or cross-file refactors.
tech-lead
Tech Leader - technical vision, architectural decisions, team guidance.