close-feature-agent

A command that checks whether a feature agent finished its assigned work, updates project status, and reports work that is now ready to start.

In plain words
What is it for?
Verifying promised files and interfaces, updating the status matrix, recording gotchas, and identifying unblocked follow-up work.
Why use it?
It catches incomplete deliverables, missing files, unsynchronised status, and undocumented discoveries at the end of an agent's task.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/paulbreuler/limps/close-feature-agent
Clone the repo
git clone --depth 1 https://github.com/paulbreuler/limps

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,784 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 8b7912f68bff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.claude/commands/close-feature-agent.md · 288 lines

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

  1. Verify completion - Check agent delivered what was promised
  2. Sync status - Update README.md status matrix
  3. Report unblocked - Show what can now proceed
  4. 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.

Read the full file on GitHub · 288 lines

Changes

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.

  1. 2d ago First seen · 288 lines · 0 tokens per session scan A 8b7912f68bff

Subscribe to this mod's changes

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.