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/alexgvozden/claude-plugin/update-featuregit clone --depth 1 https://github.com/alexgvozden/claude-pluginWrote 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/alexgvozden/claude-plugin/update-feature)<a href="https://agentmods.dev/commands/alexgvozden/claude-plugin/update-feature"><img src="https://agentmods.dev/badge/commands/alexgvozden/claude-plugin/update-feature.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 5.1 | $0.00011 | $0.01237 |
| Opus 5 | $0.00005 | $0.00619 |
| Sonnet 5 | $0.00002 | $0.00247 |
| Haiku 4.5 | $0.00001 | $0.00124 |
Grade A, and why
update-feature 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 5d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Feature Planning Document
This command updates feature plans for small to medium changes. For larger changes, use /plan-feature to recreate the plan.
Workflow
STEP 1: Analyze Change
Read planning file: {PLANNING_FILE} Analyze change: {CHANGE_DESCRIPTION}
Determine:
- What sections need updating?
- Is this minor (add feature) or major (change approach)?
- Any questions to clarify?
If unclear: Ask 1-4 questions, WAIT for response. If clear: Proceed to Step 2.
STEP 2: Propose Updates
Present a concise proposal:
# 📋 Update Proposal: [Brief title]
## Summary
[2-3 sentences explaining the change]
## Changes to Planning Document
### Requirements (if affected)
- **Add:** [New requirement]
- **Modify:** [What changes]
- **Remove:** [What's removed and why]
### Technical Design (if affected)
**Database:** [Schema changes if any]
**API:** [Endpoint changes if any]
**UI:** [Component changes if any]
### Implementation Progress Table
**New tasks to add:**
- Phase X, Task X.Y: [Description] - ⏸️ Pending
**Tasks to modify:**
- Phase Y, Task Y.Z: [Old description] → [New description]
(Keep current status: ✅/🔄/⏸️)
### Testing & Acceptance Criteria
[What needs to be updated]
## Impact Summary
- **Effort:** +[X] hours/days
- **Breaking changes:** [Yes/No - explain]
- **New dependencies:** [List if any]
---
**Review and approve:**
Type "approved" to update the planning document and proceed with implementation.
Type "feedback: [your comments]" to revise this proposal.
Type "cancel" to abort.
STOP and WAIT for user response.
STEP 3: Handle Response
If "approved":
- Update the planning document with all approved changes
- Preserve Implementation Progress table:
- Keep ✅ Complete tasks unchanged
- Keep 🔄 In Progress tasks unchanged
- Add new tasks as ⏸️ Pending with "NEW" label
- Update modified tasks with "MODIFIED" label
- Add update metadata:
*Last Updated: [Date] - [Change summary]* - Proceed to STEP 4
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.
- 5d ago First seen · 191 lines · 11 tokens per session scan A 49263888d9a7
update-feature is a command published in the GitHub repository alexgvozden/claude-plugin (11 stars, last pushed 9mo ago), licensed MIT. It adds 11 tokens to every session and 1,237 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
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.