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/paulbreuler/limps/close-feature-agentgit clone --depth 1 https://github.com/paulbreuler/limpsWhat 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 | $0.01784 |
| Opus 5 | $0.00000 | $0.00892 |
| Sonnet 5 | $0.00000 | $0.00357 |
| Haiku 4.5 | $0.00000 | $0.00178 |
Grade A, and why
close-feature-agent 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Close Feature Agent v2.0.0
Verify agent completion, sync status, and identify unblocked work.
Invocation
/close-feature-agent [path-to-agent-file]
Example:
/close-feature-agent plans/0004-feature-name/agents/000_agent_name.agent.md
What This Command Does
- Verify completion - Check agent delivered what was promised
- Sync status - Update README.md status matrix
- Report unblocked - Show what can now proceed
- Capture gotchas - Ensure discoveries are in gotchas.md
What This Command Does NOT Do
- Regenerate other agent files (use
update-feature-plan) - Modify source code
- Merge PRs
- Assign next work
Workflow
Step 1: Parse Agent File
Read the agent's .agent.md using limps MCP process_doc tool and extract:
- Feature IDs and their status
- Exported interfaces claimed
- Files that should exist
- Gotchas section
Step 2: Verify Completion
For each feature marked PASS:
Check files exist:
- [ ] src/components/Column/ColumnHeader.tsx exists
- [ ] src/components/Column/ColumnHeader.test.tsx exists
- [ ] src/components/Column/ColumnHeader.stories.tsx exists
Check exports match interface (spot check):
- [ ] useColumnHeader exports match declared signature
- [ ] ColumnHeader component exports match declared signature
Check tests pass:
- [ ] Run project test suite for affected files
Step 3: Sync Status
Update README.md status matrix using limps MCP update_doc tool:
Before:
| 2 | Headers | Columns | 🔄 WIP | - |
| 3 | Resize | Columns | ❌ GAP | #2 |
After:
| 2 | Headers | Columns | ✅ PASS | - |
| 3 | Resize | Columns | ✅ PASS | - |
Update dependency graph colors if present.
Step 4: Update Task Status
Use limps MCP update_task_status to mark features as PASS. Task status is stored in agent file frontmatter.
Agent-only plans (no feature IDs):
- If the agent file does not list feature IDs (e.g., only agent tasks), skip
update_task_status. - Add a note in the output that task status updates require feature IDs.
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 · 288 lines · 0 tokens per session scan A 8b7912f68bff
close-feature-agent is a command published in the GitHub repository paulbreuler/limps (10 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,784 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 commands, from other repositories
plan-new
Create a new plan using the Universal Planning Framework.
plan-review
Check plan quality against Universal Planning Framework standards.
interview-plan
Interview a plan using framework-aware questions across 3 depth tiers.
plan-refine
Autonomously stress-test and harden a plan through 6 adversarial perspectives.
start
Enter Fathom Mode with a task. Bare /fathom:start shows status only via hook (no LLM).
plan
Plan from the current Fathom session, grounded in a structured intent.