review-proposals

review-proposals is a skill for Claude Code from jpicklyk/task-orchestrator. It costs 129 tokens per session (4,202 once invoked), scanned A, original, MIT.

A decision process for reviewing pending improvement proposals created from repeated findings. It lets you accept, reject, or defer each proposal and applies the chosen outcome.

In plain words
What is it for?
Use it to triage retrospective proposals, update project configuration when appropriate, and file or link shared changes as GitHub issues.
Why use it?
It prevents suggested process changes from being applied without review and keeps project-specific and shared changes separate.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the task-orchestrator plugin — 15 skills shipped together

Good fit Use it to triage retrospective proposals, update project configuration when appropriate, and file or link shared changes as GitHub issues.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jpicklyk/task-orchestrator/review-proposals
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.

Any agent
npx skills add jpicklyk/task-orchestrator --skill review-proposals
Clone the repo
git clone --depth 1 https://github.com/jpicklyk/task-orchestrator

Made for: Claude Code.

Or install task-orchestrator, the plugin that ships this one along with the rest of its 15 skills.

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 review-proposals

README.md
[![agentmods](https://agentmods.dev/badge/skills/jpicklyk/task-orchestrator/review-proposals/github.svg)](https://agentmods.dev/skills/jpicklyk/task-orchestrator/review-proposals)
Your own site
<a href="https://agentmods.dev/skills/jpicklyk/task-orchestrator/review-proposals"><img src="https://agentmods.dev/badge/skills/jpicklyk/task-orchestrator/review-proposals/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for review-proposals

Your own site · 80×15
<a href="https://agentmods.dev/skills/jpicklyk/task-orchestrator/review-proposals"><img src="https://agentmods.dev/badge/skills/jpicklyk/task-orchestrator/review-proposals.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,202 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00129 $0.04202
Opus 5 $0.00064 $0.02101
Sonnet 5 $0.00026 $0.00840
Haiku 4.5 $0.00013 $0.00420

Measured 10d ago against content hash 4f2e0063ef7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-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 10d 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-plugins/task-orchestrator/skills/review-proposals/SKILL.md · 377 lines

How it starts

The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Proposals

Triages improvement-proposal MCP items created by /session-retrospective when a cross-session trend graduates. Presents pending proposals, collects a per-proposal decision, and carries out the disposition — including applying project-scoped config changes and filing/linking GitHub issues for global changes.

Shared GitHub conventions (issue template, scrub rule, gh guard, dedup procedure) are not duplicated here — see <skill-base-dir>/../session-retrospective/references/github-feedback.md for the full C2/C4/C5 contract and dedup steps referenced throughout Step 5.


Step 0 — Parse Arguments and Read Config

Parse $ARGUMENTS:

  • A UUID → single-proposal mode: skip Step 1 discovery entirely: go straight to Step 2 for that one item.
  • --scope global or --scope project → filter Step 1 discovery to only that scope's query. Absent → run both discovery queries.
  • Neither → full discovery, both scopes.

Read the workspace .taskorchestrator/config.yaml directly (file read, not MCP) for:

  • project.rootId / project.name — enables the project-scoped discovery query and per-root push in Step 5. If absent, project-scoped discovery and project-scoped acceptance are unavailable — proceed with global-only discovery.
  • retrospective.github_feedback.enabled — default false if the block or key is absent.
  • retrospective.github_feedback.repo — default jpicklyk/task-orchestrator if absent.

Step 1 — Discovery

Skip this step entirely in single-proposal mode (UUID argument supplied).

Run both queries in parallel (unless --scope narrows to one):

Global:

query_items(operation="search", query="Improvement Proposals", limit=5)

Find the "Improvement Proposals" container from the result, then:

query_items(operation="overview", anchorId="<container-uuid>", includeChildren=true)

Project-scoped (only if project.rootId is known):

query_items(operation="search", tags="improvement-proposal", ancestorId="<rootId>", limit=50)

Read the full file on GitHub · 377 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. 10d ago First seen · 377 lines · 129 tokens per session scan A 4f2e0063ef7a

Subscribe to this mod's changes

review-proposals is a skill published in the GitHub repository jpicklyk/task-orchestrator (206 stars, last pushed 1mo ago), licensed MIT. It adds 129 tokens to every session and 4,202 once invoked, about $0.0006 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.