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 skills add DailybotHQ/deepworkplan-skill --skill refinegit clone --depth 1 https://github.com/DailybotHQ/deepworkplan-skillWrote 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/refine)<a href="https://agentmods.dev/skills/dailybothq/deepworkplan-skill/refine"><img src="https://agentmods.dev/badge/skills/dailybothq/deepworkplan-skill/refine/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/refine"><img src="https://agentmods.dev/badge/skills/dailybothq/deepworkplan-skill/refine.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 | $0.00050 | $0.05521 |
| Opus 5.5 | $0.00020 | $0.02208 |
| Sonnet 5.5 | $0.00010 | $0.01104 |
| Haiku 4.5 | $0.00005 | $0.00552 |
Grade A, and why
deepworkplan-refine 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 — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeepWorkPlan — Refine
Modify an existing plan (add / edit / split / reorder tasks, update the README, promote a Lite plan to Full, or — only on explicit request — migrate a legacy ending or a v5 plan to v6).
No drafts (2.4.0):
creatematerializes an executable Lite plan directly, so there is nothing to "refine into a plan" any more.refineoperates on a plan folder under.dwp/plans/. The.dwp/drafts/directory and thePLAN_{name}_draft_refined.mdartifact were removed in 2.4.0.
Shared resources (read these)
../shared/dwp-paths.md— plans at.dwp/plans/, plans at.dwp/plans/<plan>/.../shared/context.sh— resolvedwp_dir.- Guide (essential — read for this flow):
../guide/authoring.md(plan README §4, task-file anatomy §5 incl. the Touched Surface, mandatory elements) and../guide/structure.md(§1–§2 naming and folders). - Guide (conditional — read only when the trigger fires):
../guide/orchestrator.md/../guide/team-agents.mdonly for plans that use them;../guide/execution.md§6.1 when editing the Final Review (or a legacy plan's final tasks). Do not read other guide files for this flow;../guide/GUIDE.mdis the routing index, consulted only when a section is not named above. - Shared contract (conditional — read the named steps only when the trigger fires):
../create/SKILL.mdSteps 3.5–3.7 and 4.4–4.5 when promoting a Lite plan, adding or splitting a task, completing a partial materialization, or migrating — the one contract for task anatomy, gate selection, the Final Review, the ledger, the write order and the plan-quality check (refine never has a second template);../spec/PLAN_STATE.md§5–§6 when the plan carriesstate.json(regeneration, evidence invalidation) or onmigrate(the declared-migration line). - Conditional — read only when the trigger fires:
../examples/CREATE_PLAN.md— prompt patterns for professional rewriting; read it when rewriting plan-level structure or authoring new plan sections — task-level edits and promotions need only the contracts named above.
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 3c08222527f9
- 4d ago Changed 591796407c99
- 5d ago Changed 2369e1352756
- 6d ago Changed 0bf9d97eb2eb
- 7d ago Changed · +2 lines b3e561b7bfd4
- 9d ago Changed 68cc66fb41ab
- 11d ago Changed a72639838f1f
- 15d ago Changed 8189f85bbea3
- 18d ago Changed · +37 lines 8aa778b2bbfe
- 29d ago First seen · 317 lines · 50 tokens per session scan A 10197837a51f
deepworkplan-refine is a skill published in the GitHub repository DailybotHQ/deepworkplan-skill (23 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 5,521 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.