deepworkplan-execute

deepworkplan-execute is a skill for Claude Code from DailybotHQ/deepworkplan-skill. It costs 39 tokens per session (9,927 once invoked), scanned A, original, MIT.

A tool for carrying out an existing Deep Work Plan, which is a repository task plan stored in .dwp/plans/.

In plain words
What is it for?
Use it to select or resume a plan, complete its tasks in order, validate the results, commit progress, and record the plan state.
Why use it?
It turns a written plan into a tracked sequence of implementation tasks with checks after each task.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

Good fit Use it to select or resume a plan, complete its tasks in order, validate the results, commit progress, and record the plan state.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dailybothq/deepworkplan-skill/execute
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 DailybotHQ/deepworkplan-skill --skill execute
Clone the repo
git clone --depth 1 https://github.com/DailybotHQ/deepworkplan-skill

Made for: Claude Code.

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 deepworkplan-execute

README.md
[![agentmods](https://agentmods.dev/badge/skills/dailybothq/deepworkplan-skill/execute/github.svg)](https://agentmods.dev/skills/dailybothq/deepworkplan-skill/execute)
Your own site
<a href="https://agentmods.dev/skills/dailybothq/deepworkplan-skill/execute"><img src="https://agentmods.dev/badge/skills/dailybothq/deepworkplan-skill/execute/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 deepworkplan-execute

Your own site · 80×15
<a href="https://agentmods.dev/skills/dailybothq/deepworkplan-skill/execute"><img src="https://agentmods.dev/badge/skills/dailybothq/deepworkplan-skill/execute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,927 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.
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 $0.00039 $0.09927
Opus 5.5 $0.00016 $0.03971
Sonnet 5.5 $0.00008 $0.01985
Haiku 4.5 $0.00004 $0.00993

Measured 3d ago against content hash 810f9ca1039d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 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.

.agents/skills/deepworkplan/execute/SKILL.md · 678 lines

How it starts

The opening of the file, as written. The whole thing — 678 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 — fluently inside the plan's authorization, without asking whether to continue after every successful task.

Shared resources (read at their moment, not upfront)

The compulsory set for this flow is the router SKILL plus this file: every rule the loop runs on — strict order, gate selection from the actual surface, STOP-on-fail, task-local closure, commit format, the state-update command, the Final Review — is stated inline in the steps below. A default session reads no guide, spec or shared companion before Task 1; companions load when their moment arrives. (This ordering is deliberate: reading companions "to be safe" is the failure mode this tiering removed.)

  • Essential now (before the first task): ../shared/context.sh — run it (bash ../shared/context.sh) to resolve repo root, branch, agent tool and dwp_dir; its source is not part of this flow's reads. That is the whole t0 set — the operative rules the loop needs are inline below.
  • Conditional — read only when the trigger fires:
    • v6.md (this directory) — read only when Step 2.0 detects a v6 or v7 plan; it carries the whole task loop.
    • delegation.md — read only when a v7 plan granting agent_delegation delegates a task.
    • ../guide/swarm.md §17 — read only when the agentkit addon is enabled (capacity check at each task boundary: ../shared/swarm.py capacity) or a handoff or succession is in play.
    • ../spec/LITE_PLANS.md — read only when the plan README declares Plan Format: Lite or a v2 state line (anchored task records, approval axis, promotion recovery).
    • ../spec/PLAN_STATE.md §4–§5 — read only when state.json and the README disagree (markdown wins — regenerate), when a takeover needs the checkpoint contract, or when update-state.py cannot run and a whole-file rewrite is unavoidable. The everyday needs are inline: bookkeeping order and the closed gate-record shape in Step 5 rules 5–6.
    • ../guide/execution.md — read §6.1 only when the Final Review task begins (the prose behind its five parts (a)–(e)); read the Multi-Project Commit Workflow only when the plan spans multiple repositories; read rule 6 only when a Dailybot report moment arrives with the addon installed. The loop rules (§6 rules 1–5) and completion tracking are already inline in Step 5 and Important Notes.
    • ../guide/authoring.md §5.3–§5.4 — read only when judging a task's test or security discipline.
    • ../guide/prompts.md §9 — read only when a resume scenario arises mid-execution (the resume sub-skill owns them).
    • ../shared/adaptation.md — read only when adapting a pack example or template command into repo-specific form; the operative rule — select from the actual surface, never a fixed command set — is inline in Step 5 rule 3.
    • ../shared/dwp-paths.md — read only when a plan folder cannot be located or the DWP_DIR override is in play (Steps 0–3 already inline .dwp/plans/<plan>/).
    • ../shared/troubleshooting.md — read only when something is already wrong (discovery failure, stale installation, missing test command, unsupported host capability, inconsistent plan state).
    • orchestrator.md (this directory) plus ../guide/orchestrator.md §13 — read only when Step 2.1 detects an orchestrator plan.
    • team-agents.md (this directory) plus ../guide/team-agents.md §14 — read only when Step 2.2 finds a Team Agents Configuration and team mode is selected.
    • ../create/addon-augmentations.md — read only when the Final Review runs its required local-review pass (load it even if the reviewer is not yet installed, so the missing-install finding path is available); the reviewer's own ../addons/ai-diff-reviewer/SKILL.md loads at that same moment, never before.
    • The repository's docs/TESTING_GUIDE.md — read only when a task's gate must be widened or derived.
    • ../guide/GUIDE.md — the routing index; consult only when a need is not covered by a section named above.
  • Never by default: no other guide, spec, preset or addon file is read for this flow — not defensively, not "to be safe". Speculative reading is exactly what the tier above replaces: name the moment, then read.

Read the full file on GitHub · 678 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 Changed 810f9ca1039d
  2. 4d ago Changed · +1 lines 35682a21d69a
  3. 5d ago Changed 72ecdb2ac14b
  4. 6d ago Changed d242bd36d62a
  5. 7d ago Changed · +1 lines cc01a3855dd0
  6. 9d ago Changed f95080a5ffac
  7. 11d ago Changed 6bd7a506857e
  8. 15d ago Changed ce3735becd92
  9. 18d ago Changed · +12 lines b8a6ecb8c1fe
  10. 29d ago First seen · 664 lines · 39 tokens per session scan A 6d358c01a782

Subscribe to this mod's changes

deepworkplan-execute is a skill published in the GitHub repository DailybotHQ/deepworkplan-skill (23 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 9,927 once invoked, about $0.0002 per session on Opus 5.5. 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.