agentmods.dev

work-idea

work-idea is a skill for Claude Code, Codex from paultyng/ideate. It costs 70 tokens per session (2,686 once invoked), scanned A, original, MIT.

A workflow for catching up on and resuming one idea in a local Ideate workspace.

In plain words
What is it for?
Use it when switching to an idea, resuming one, or finding the session associated with a particular idea name, slug, or identifier.
Why use it?
It brings together the idea’s tasks, linked resources, recent activity, and running or paused work, so you can understand its state before continuing.

Skill for Claude CodeCodex

not rated 9 16d ago A scan 70 tokens original MIT
View the source file paultyng/ideate
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/paultyng/ideate/work-idea
Any agent
npx skills add paultyng/ideate --skill work-idea
Clone the repo
git clone --depth 1 https://github.com/paultyng/ideate

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 work-idea

README.md
[![agentmods](https://agentmods.dev/badge/skills/paultyng/ideate/work-idea.svg)](https://agentmods.dev/skills/paultyng/ideate/work-idea)
Your own site
<a href="https://agentmods.dev/skills/paultyng/ideate/work-idea"><img src="https://agentmods.dev/badge/skills/paultyng/ideate/work-idea.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,686 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 $0.00070 $0.02686
Opus 5 $0.00035 $0.01343
Sonnet 5 $0.00014 $0.00537
Haiku 4.5 $0.00007 $0.00269

Measured 3d ago against content hash 166c5784e0c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

work-idea 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.

internal/skills/canonical/work-idea/SKILL.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

work-idea

Workflow for producing a detailed brief on one Ideate idea, then navigating into its session.

The unit of work is the idea. Sessions are one facet of an idea, alongside the backlog (tasks queued or mid-flight), resources (linked artifacts), and recent activity. The brief covers the whole idea, not just whatever session happens to be running.

Inputs

The user supplies an identifier for the target. Resolve in this order:

  1. Session UUID (matches ^[0-9a-f-]{36}$) — resolve to its owning idea via the sessions.running / sessions.dormant UUIDs on each list_ideas row.
  2. Idea slug (exact match).
  3. Idea name (case-insensitive substring).
  4. Fuzzy keyword from the user's phrasing (e.g. "the boilerplate idea", "the search migration", "JWKS").

If the input matches zero ideas or more than one, stop and ask the user to disambiguate. Do not guess.

Steps

  1. Batched workspace fetch. Call ideate:list_ideas with include_output_lines: 120. The result carries every non-archived idea's summary, backlog counts + in-progress titles, sessions.running + sessions.dormant lists, last_activity_at, AND the most-recent running session's last 120 lines of screen — enough context to recover detailed state on the resolved idea. Resolve the user's input against the returned rows using the order above.

  2. (Optional) cross-references. If the user's phrasing carries a URL (PR link, doc URL), call ideate:match_resource_urls to confirm the resolution and check whether the URL appears on sibling ideas the user might also want to know about. Mention sibling hits in the brief, do not switch to them.

  3. Parse the running session's tail (if any) for:

    • Working branch (from the worktree banner, e.g. testagent@refactor/rootflags-shared wt).
    • Recent commits or pushes (commit subjects, PR numbers).
    • Open question(s), verbatim if short.
    • Any explicit "Next:" / "TODO:" markers the agent emitted.
    • PR / Jira / Slack links surfaced in the last screen.
    • Spinner state (✻/✳/Doing…/Running…) to flag if the agent is mid-turn.

Read the full file on GitHub · 232 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. 3d ago First seen · 232 lines · 70 tokens per session scan A 166c5784e0c5

Subscribe to this mod's changes

work-idea is a skill published in the GitHub repository paultyng/ideate (9 stars, last pushed 16d ago), licensed MIT. It adds 70 tokens to every session and 2,686 once invoked, about $0.0003 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.

Planningagent-orchestrationai-agentclaude-codedesktop-appgoidea-management
Related

Other skills, from other repositories

challenge

Adversarial review skill. Use when the user wants to stress-test an idea, argument, proposal, or opinion from multiple independent angles. Spawns parallel Hydra workers with orthogonal analytical methodologies.

blueberrycongee/termcanvas · 41 tokens

code-review

Structured code review skill. Use when asked to "review this code", "review this PR", "check this diff", or when acting as a Hydra reviewer. Runs a multi-pass review with specialist focus areas and confidence-gated findings.

blueberrycongee/termcanvas · 50 tokens

qa

QA testing skill with real browser automation. Use when asked to "test this site", "QA this page", "check for visual bugs", "verify the deploy", or when Hydra needs browser validation for UI changes. Requires the browse binary.

blueberrycongee/termcanvas · 50 tokens

fix-issues

Auto-fix GitHub issues labeled as bugs: fetch open bug issues, analyze feasibility, fix code, and submit PRs. One issue per invocation. Use when: (1) User says "/fix-issues", (2) User asks to fix GitHub issues.

FerroxLabs/wayland · 59 tokens

fix-sentry

Auto-fix high-frequency Sentry issues: fetch issues > N occurrences, analyze stack traces, fix code, create GitHub issues, and submit PRs. Supports user feedback issues (event.type "default") with attachment analysis (logs, screenshots) when includefeedback=true. Use when: (1) User says "/fix-sentry", (2) User asks to…

FerroxLabs/wayland · 83 tokens

pr-automation

PR Automation Orchestrator: poll open PRs, check CI, run review, fix, and merge eligible PRs. Use when: (1) Invoked by daemon via scripts/pr-automation.sh, (2) User says "/pr-automation".

FerroxLabs/wayland · 56 tokens