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/catlog22/claude-code-workflow/analyze-with-filegit clone --depth 1 https://github.com/catlog22/Claude-Code-WorkflowWhat 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 | $0.00019 | $0.07050 |
| Opus 5 | $0.00010 | $0.03525 |
| Sonnet 5 | $0.00004 | $0.01410 |
| Haiku 4.5 | $0.00002 | $0.00705 |
Grade A, and why
analyze-with-file 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 — 688 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use when: architecture review, implementation analysis, concept exploration, decision evaluation, or any multi-perspective codebase question.
Auto mode (-y): Auto-confirm decisions, use recommended angles, skip interactive scoping.
Artifacts
{projectRoot}/.workflow/.analysis/ANL-{date}-{slug}/
├── discussion.md # Single source of truth: rounds, decisions, synthesis, conclusions, recommendations
├── state.json # Session state: config, confidence, quality tracking
├── exploration-codebase.json # Layer 1 shared discovery: files, patterns, module map
├── explorations/{perspective}.json # Layer 2-3 per-perspective deep-dives (multi-perspective only)
├── research.json # External research: best practices, pitfalls, sources
└── handoff.json # Structured handoff (only on "执行任务")
| File | When | Schema |
|---|---|---|
discussion.md |
Phase 1+ | All analysis content: metadata, rounds, multi-perspective synthesis, conclusions, recommendations, intent/findings coverage matrices |
state.json |
Phase 0+ | session_id, topic, depth, dimensions[], perspectives[], focus_areas[], current_round, current_phase, confidence{dimensions{}, overall, weakest, history[]}, quality{pressure_pass_done, challenge_modes_used[], stall_counter, last_findings_count, readiness_gate_passed, residual_risks[]} |
exploration-codebase.json |
Phase 2 | session_id, timestamp, topic, dimensions[], relevant_files[{path, annotation, dimensions[]}], patterns[], module_map{}, questions_for_user[], _metadata |
explorations/{name}.json |
Phase 2 | perspective, relevant_files[], key_findings[], code_anchors[{file, lines, snippet, significance}], call_chains[{entry, chain, files}], questions_for_user[], _metadata |
research.json |
Phase 2 | topic, mode, timestamp, findings[{finding, detail, confidence, source_url}], best_practices[{practice, rationale, source}], alternatives[{option, pros, cons, verdict}], pitfalls[{issue, mitigation, source}], codebase_gaps[{gap, current_approach, recommended_approach}], sources[{title, url, key_takeaway}] |
handoff.json |
Phase 4 | source, session_id, session_folder, summary, implementation_scope[{objective, rationale, priority, target_files[], acceptance_criteria[], change_summary}], code_anchors[], key_files[], key_findings[], decision_context[], exploration_artifacts{exploration_codebase, explorations, perspectives, research, deep_dives[]} — keys align with workflow-lite-plan artifactMapping |
Removed from separate files (now in discussion.md): explorations.json, perspectives.json, conclusions.json. Synthesis, conclusions, and recommendations are written directly to discussion.md sections.
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 · 688 lines · 19 tokens per session scan A fa8b221a8679
analyze-with-file is a command published in the GitHub repository catlog22/Claude-Code-Workflow (2,134 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 7,050 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 commands, from other repositories
verify-claim
Walk a claim through the SIFT method (Stop, Investigate, Find better coverage, Trace).
beat-brief
Draft a daily beat briefing from the files in sample-docs/.
cross-review
Run GitHub Copilot CLI and OpenAI Codex against the current git diff for cross-model review.
spec-design
Create comprehensive technical design for a specification.
step-research
Always research before proposing a fix. The Untether bug you're chasing is often a known upstream engine quirk, a previously-fixed regression, or a documented config gotcha.
ox-session-review
Command "ox-session-review" from sageox/ox, covering failure-mode watch-list (read first), from the ledger root. should print 0, phase 1 — scan & score (read-only), quality buckets (first match wins) and removal candidates.