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/update-feature-plangit clone --depth 1 https://github.com/paulbreuler/limpsWrote 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/commands/paulbreuler/limps/update-feature-plan)<a href="https://agentmods.dev/commands/paulbreuler/limps/update-feature-plan"><img src="https://agentmods.dev/badge/commands/paulbreuler/limps/update-feature-plan.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.02573 |
| Opus 5 | $0.00000 | $0.01287 |
| Sonnet 5 | $0.00000 | $0.00515 |
| Haiku 4.5 | $0.00000 | $0.00257 |
Grade A, and why
update-feature-plan 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 — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Feature Plan v2.0.0
Apply feedback to an existing plan, regenerate affected agent files, and commit after approval.
Key Change from v1.x
Old: Update plan.md + speed_prompts.md (summaries)
New: Update plan.md + regenerate affected agents/*.agent.md (distilled execution files)
Agent files are distilled, not copied. When plan changes, affected agent files must be regenerated.
Invocation
/update-feature-plan [plan-name-or-path]
Workflow
1. Identify plan
2. Gather feedback
3. Read current state
4. Analyze & propose changes
5. User approves
6. Apply to plan file, interfaces.md
7. Identify affected agents
8. Regenerate affected agent files (distill, don't copy)
9. Verify consistency
10. Commit
11. Assess status: `limps next-task <plan-name>` (optional, see next task)
After Update
After updating a plan and regenerating agent files:
- Assess plan status: Run
limps status <plan-name>to see overall plan status - Start next work: Use
limps next-task <plan-name>to get the next task, then use/run-agent <plan-name>to start it
This helps ensure the plan is in a good state after updates and ready for continued work.
Instructions
1. Identify the Plan
Use /limps-plan-operations identify-plan skill for consistent plan identification:
- Ask: "Which plan to update?"
- If unsure: Use
limps list-plansor limps MCPlist_planstool - Confirm plan directory exists
2. Gather Feedback
Accept feedback via:
- Paste directly
- File path:
@feedback.md - Description: "Add accessibility to #3"
Parse feedback for:
- Feature changes (add/remove/modify)
- Interface changes (affects downstream agents)
- Status updates
- Gotcha discoveries
- Dependency changes
- Test coverage gaps
3. Read Current State
Use /limps-plan-operations load-artifacts skill for consistent artifact loading:
[plan-name]/
├── README.md
├── {plan-name}-plan.md # Full verbose specs
├── interfaces.md # Contract source of truth
├── gotchas.md
└── agents/
└── *.agent.md # Minimal execution files
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 · 408 lines · 0 tokens per session scan A 598cf2f89fb0
update-feature-plan 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 2,573 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
workflow-from-spec
Design a complete multi-agent workflow from a natural language description, selecting the right orchestration pattern.
commit
Run when user calls /commit or asks to generate a commit message. Analyzes staged changes and writes a structured commit message.
plan-review
Check plan quality against Universal Planning Framework standards.
setup
Fetch Kobiton credentials from the authenticated MCP server and write them to /.kobiton/.credentials.
implement
Execute implementation by processing atomic task files one at a time with Context Pinning (Atomic Traceability Model).
_registry-protocol
This protocol is MANDATORY for ALL commands, agents, and phases.