apply-proposals

apply-proposals is a skill for Claude Code, Codex from dixus/claudeframework. It costs 40 tokens per session (1,505 once invoked), scanned A, original, MIT.

A tool for applying accepted improvement proposals from a learn-proposals.md file to skills and rule files. Proposals describe a change, its reason, its source, its status, and the suggested edit.

In plain words
What is it for?
Use it after reviewing proposals to update selected skill or rule files, either by applying every accepted proposal, applying a specific proposal, or choosing proposals interactively.
Why use it?
It closes the loop between identifying lessons and changing the files that guide future work. It also lets you apply all accepted proposals, choose one by number, or review pending proposals interactively.

Skill for Claude CodeCodex

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 skills/dixus/claudeframework/apply-proposals
Any agent
npx skills add dixus/claudeframework --skill apply-proposals
Clone the repo
git clone --depth 1 https://github.com/dixus/claudeframework

Made for: Claude Code, Codex.

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 apply-proposals

README.md
[![agentmods](https://agentmods.dev/badge/skills/dixus/claudeframework/apply-proposals.svg)](https://agentmods.dev/skills/dixus/claudeframework/apply-proposals)
Your own site
<a href="https://agentmods.dev/skills/dixus/claudeframework/apply-proposals"><img src="https://agentmods.dev/badge/skills/dixus/claudeframework/apply-proposals.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,505 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 $0.00040 $0.01505
Opus 5 $0.00020 $0.00753
Sonnet 5 $0.00008 $0.00301
Haiku 4.5 $0.00004 $0.00151

Measured 5d ago against content hash 46934255fbce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

apply-proposals 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.

.claude/skills/apply-proposals/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apply accepted proposals from .claude/reviews/learn-proposals.md to the target skill and rule files.

$ARGUMENTS is optional:

  • --all — apply all proposals with Status accepted
  • --proposal <N> — apply only proposal number N (by order of appearance), regardless of Status
  • No arguments — interactive mode: present pending proposals for review, then apply accepted ones

Step 0 — Load proposals

  1. Read .claude/reviews/learn-proposals.md. If the file doesn't exist, report "No proposals file found. Run /scout or /learn first." and stop.
  2. Parse each proposal block. A proposal starts with ### Skill: or ### New skill: or ### Rule: and contains:
    • **What:** — one-line description
    • **Why:** — motivation
    • **Source:** or **Source tier:** — provenance
    • **Status:** — pending / accepted / rejected / deferred
    • **Diff:** — the proposed change (old → new)
  3. Build a numbered list of all proposals with their Status.

Step 1 — Select proposals to apply

If --all: select every proposal with Status accepted.

If --proposal <N>: select only that proposal. If its Status is not accepted, ask: "Proposal #N has status <status>. Apply anyway? (Y/N)" — proceed only if Y.

If no arguments (interactive mode):

  1. Print all proposals in a numbered table:
    | #  | Target            | What                          | Status   | Tier |
    | -- | ----------------- | ----------------------------- | -------- | ---- |
    | 1  | /2_review         | Add disallowedTools           | pending  | T1   |
    | 2  | /3_fix            | Add maxTurns: 15              | pending  | T1   |
    
  2. Ask: "Which proposals to apply? Enter numbers (e.g. 1,3,5), all for all pending, or q to quit."
  3. For each selected proposal, update its Status to accepted in learn-proposals.md before applying.

If no proposals are selected (or all are already accepted/rejected), report and stop.

Step 2 — Validate diffs before applying

Read the full file on GitHub · 132 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 · 132 lines · 40 tokens per session scan A 46934255fbce

Subscribe to this mod's changes

apply-proposals is a skill published in the GitHub repository dixus/claudeframework (10 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 1,505 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens