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/try-works/recursive-mode/recursive-closeoutgit clone --depth 1 https://github.com/try-works/recursive-modeWhat 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 | $0.00733 |
| Opus 5 | $0.00000 | $0.00367 |
| Sonnet 5 | $0.00000 | $0.00147 |
| Haiku 4.5 | $0.00000 | $0.00073 |
Grade A, and why
recursive-closeout 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.
How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
recursive-closeout (prompt template)
Scaffold Phases 4-8 from existing evidence and control-plane docs instead of starting from a blank markdown file.
Usage Pattern
Scaffold recursive closeout phase: <run-id> <04|05|06|07|08>
Script (Recommended)
python "<SKILL_DIR>/scripts/recursive-closeout.py" --repo-root . --run-id "<run-id>" --phase 04
python "<SKILL_DIR>/scripts/recursive-closeout.py" --repo-root . --run-id "<run-id>" --phase 05 --preview-log ".recursive/run/<run-id>/evidence/logs/preview-server.log"
python "<SKILL_DIR>/scripts/recursive-closeout.py" --repo-root . --run-id "<run-id>" --phase 08 --force
pwsh -NoProfile -File "<SKILL_DIR>/scripts/recursive-closeout.ps1" -RepoRoot . -RunId "<run-id>" -Phase 04
pwsh -NoProfile -File "<SKILL_DIR>/scripts/recursive-closeout.ps1" -RepoRoot . -RunId "<run-id>" -Phase 05 -PreviewLog ".recursive/run/<run-id>/evidence/logs/preview-server.log"
pwsh -NoProfile -File "<SKILL_DIR>/scripts/recursive-closeout.ps1" -RepoRoot . -RunId "<run-id>" -Phase 08 -Force
What It Does
- Scaffolds
04-test-summary.md,05-manual-qa.md,06-decisions-update.md,07-state-update.md, or08-memory-impact.md - Prefills the required header fields
- Prefills the required phase sections and audited sections
- Prefills late-phase input/output lists using the current run state
- Reuses the Phase 0 executable diff basis inside audited closeout scaffolds
- Optionally parses the actual preview URL from a preview-server log and injects it into Phase 5
- Scaffolds late-phase requirement disposition lines using the current machine-checkable status model
- Includes
/.recursive/memory/skills/SKILLS.mdin Phase 8 closeout scaffolds so skill-memory maintenance is explicit - For Phase 8, scaffolds
## Run-Local Skill Usage Captureand## Skill Memory Promotion Reviewso skill lessons are captured before they are promoted into durable memory - If Phase 8 is already locked, rerunning
recursive-closeoutfor phase08calls/.recursive/scripts/recursive-training-phase8-trigger.py --auto
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 · 48 lines · 0 tokens per session scan A 7495e10655dd
recursive-closeout is a command published in the GitHub repository try-works/recursive-mode (129 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 733 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 2026-08-30.
Other commands, from other repositories
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.