update-feature

update-feature is a command for coding agents from alexgvozden/claude-plugin. It costs 11 tokens per session (1,237 once invoked), scanned A, original, MIT.

A command for updating an existing plan for a small or medium-sized feature when requirements change. It reads the planning document, determines which parts are affected, and proposes the needed updates.

In plain words
What is it for?
Use it to add, modify, or remove planned work after a new requirement appears. For a larger change that needs a new approach, the input directs you to recreate the plan instead.
Why use it?
It keeps requirements, technical decisions, implementation tasks, and testing criteria aligned as a feature changes.

Command

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/alexgvozden/claude-plugin/update-feature
Clone the repo
git clone --depth 1 https://github.com/alexgvozden/claude-plugin

Wrote 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.

agentmods badge for update-feature

README.md
[![agentmods](https://agentmods.dev/badge/commands/alexgvozden/claude-plugin/update-feature.svg)](https://agentmods.dev/commands/alexgvozden/claude-plugin/update-feature)
Your own site
<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>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,237 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 5.1 $0.00011 $0.01237
Opus 5 $0.00005 $0.00619
Sonnet 5 $0.00002 $0.00247
Haiku 4.5 $0.00001 $0.00124

Measured 5d ago against content hash 49263888d9a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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.

commands/update-feature.md · 191 lines

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":

  1. Update the planning document with all approved changes
  2. 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
  3. Add update metadata: *Last Updated: [Date] - [Change summary]*
  4. Proceed to STEP 4

Read the full file on GitHub · 191 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. 5d ago First seen · 191 lines · 11 tokens per session scan A 49263888d9a7

Subscribe to this mod's changes

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.