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 skills/dailybothq/deepworkplan-skill/executenpx skills add DailybotHQ/deepworkplan-skill --skill executegit clone --depth 1 https://github.com/DailybotHQ/deepworkplan-skillWhat 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 | $0.00045 | $0.04230 |
| Opus 5 | $0.00023 | $0.02115 |
| Sonnet 5 | $0.00009 | $0.00846 |
| Haiku 4.5 | $0.00005 | $0.00423 |
Grade A, and why
deepworkplan-execute 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 2d 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 — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeepWorkPlan — Execute
Execute a Deep Work Plan by working through its tasks sequentially, one at a time, validating and committing after each, and reporting progress.
Shared resources (read these)
../shared/context.sh— resolve repo root, branch, agent tool, anddwp_dir(the.dwp/output location).../shared/dwp-paths.md— plans live at.dwp/plans/PLAN_{name}/.../shared/adaptation.md— the two repository archetypes (individual repo vs orchestrator hub) that govern how navigation and validation commands resolve.../guide/GUIDE.md— execution rules (§6), orchestrator protocol (§13), team agents (§14).../spec/PLAN_STATE.md— the machine-readable state layer (manifest.json+state.json); update it at every completion when the plan carries it.
Parameter Support
/dwp-execute {plan_name}— execute directly (skip the selection menu)./dwp-execute latest— execute the most recently modified plan.- No parameter → interactive selection (Step 1).
Normalize names by adding the PLAN_ prefix if missing. Validate that
.dwp/plans/PLAN_{name}/ and its README.md exist; if not, show available plans
and ask the user to choose.
Workflow
Step 0 — Check for Parameters
If a parameter was given, resolve the plan (or "latest"), validate the folder and
README under .dwp/plans/, and skip to Step 2. Otherwise continue to Step 1.
Step 1 — Identify Plan
List folders in .dwp/plans/ starting with PLAN_; mark the most recently
modified as latest. Present a numbered menu and accept a number, plan name, or
latest. Validate the chosen plan's folder + README.
Step 2 — Read Plan Overview
Read the plan README: goal, context, global guidelines, task list ([x] vs
[ ]), execution rules.
Step 2.1 — Detect plan type. Set plan_type = "orchestrator" if the README
has a "Child DWP Plans" section, or task files contain create_child_dwp /
execute_child_dwp. Note the execution mode (Distributed / Sequential / Sequential
with Output Handoff) and whether ORCHESTRATOR_MANIFEST.md exists in the plan
folder. Report orchestrator plans with their execution mode, manifest
availability, and child-DWP list.
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.
- 2d ago First seen · 308 lines · 45 tokens per session scan A 5558c325a800
deepworkplan-execute is a skill published in the GitHub repository DailybotHQ/deepworkplan-skill (20 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 4,230 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…