Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/DailybotHQ/deepworkplan-skillnpx agentmods add skills/dailybothq/deepworkplan-skill/createWrote 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.
[](https://agentmods.dev/skills/dailybothq/deepworkplan-skill/create)<a href="https://agentmods.dev/skills/dailybothq/deepworkplan-skill/create"><img src="https://agentmods.dev/badge/skills/dailybothq/deepworkplan-skill/create/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.
<a href="https://agentmods.dev/skills/dailybothq/deepworkplan-skill/create"><img src="https://agentmods.dev/badge/skills/dailybothq/deepworkplan-skill/create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00051 | $0.13685 |
| Opus 5.5 | $0.00020 | $0.05474 |
| Sonnet 5.5 | $0.00010 | $0.02737 |
| Haiku 4.5 | $0.00005 | $0.01368 |
Grade A, and why
deepworkplan-create 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.
How it starts
The opening of the file, as written. The whole thing — 887 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeepWorkPlan — Create
Create a new Deep Work Plan through a smooth, unified flow: the developer
provides information once, you run the requirements analysis, and materialize
a Lite plan folder under .dwp/plans/PLAN_<id>_<slug>/. Guided mode presents that
proposal for review; trust chooses its ready representation without a review.
Both modes return control to the developer to execute later.
Lite-first (v2.4):
createwrites no draft file and no.dwp/drafts/directory. A Lite plan is a complete proposal, not a partial Full plan — it is the reviewable artifact the refined draft used to be, except that it is already executable. Therefined-draft/from-refined-draftcommands were removed in 2.4.0; see../spec/LITE_PLANS.md.
Lite-first command grammar
Parse boundary options before interpreting the remaining text. trust and
auto select trust mode; lite and full express an optional format
preference. Each may be a contiguous token at the beginning or end, in either
order: /dwp-create trust lite add retry, /dwp-create add retry lite trust,
/dwp-create trust add retry, and /dwp-create add retry full are equivalent
forms. Remove all recognized boundary options before classifying context.
Repeated identical options are harmless. lite plus full is an explicit
conflict: report it rather than guessing. -- ends option parsing; everything
after it is literal context. Do not scan the middle of context, quotations or
code for option words. trust with no context asks for the goal. The resulting
plan is handed off; create never modifies product source or calls execute.
Lite-first lifecycle
Step 0.3 routes new plans on this pack to v6.md. The steps below
retain v5 compatibility.
Write manifest.json, README.md, PROGRESS.md, PROMPTS.md, appropriate
analysis_results/ and state.json using the v5 schemas. A Lite README has
one shared rules section and compact anchored task records (#task-N) containing
goal, touched surface, acceptance criteria, validation and completion evidence.
It includes an inline Final Review. It does not create task files or boilerplate
solely to meet a task count. materializing, ready and promoting are distinct
from review approval and execution status.
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.
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.
- 3d ago Changed 5a53ef3a6ff6
- 4d ago Changed 5543f002a87c
- 5d ago Changed 2bb1d80c1e30
- 6d ago Changed 86e222a778ae
- 7d ago Changed 9427bbc5b9f7
- 9d ago Changed 74792fbfc6f9
- 10d ago Changed 2de500ff2fe8
- 11d ago Changed c15465da7412
- 15d ago Changed b848f805d53e
- 18d ago First seen · 887 lines · 51 tokens per session scan A d05058220388
deepworkplan-create is a skill published in the GitHub repository DailybotHQ/deepworkplan-skill (23 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 13,685 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.
Other skills, from other repositories
gsd-plan-review-convergence
Cross-AI plan convergence - replan until review concerns are resolved.
gsd-ns-manage
config workspace | workstreams thread update ship inbox.
gsd-validate-phase
Retroactively audit and fill Nyquist validation gaps for a completed phase.
dependency-upgrade
Plan, batch, and verify dependency upgrades safely. Triages outdated packages into risk tiers, upgrades in order (dev/minor/patch first, runtime majors last), verifies each batch, and produces an auditable commit sequence. Use when asked to "upgrade deps", "bump packages", "update nodemodules", "fix vulnerabilities"…
forensics
Post-mortem a failed GSD auto-mode run. Traces symptom to root cause via .gsd/ activity, journal, metrics, and lock artifacts, producing a filing-ready bug report with file:line refs and a fix suggestion. Use when asked to "forensics", "post-mortem", "why did auto-mode fail", "trace the stuck loop", "debug the crash"…
review
Review code changes for security, performance, bugs, and quality. Reviews staged changes, unstaged changes, specific commits, or PR-ready diffs.