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 setupgit 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/setup)<a href="https://agentmods.dev/skills/dailybothq/deepworkplan-skill/setup"><img src="https://agentmods.dev/badge/skills/dailybothq/deepworkplan-skill/setup/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/setup"><img src="https://agentmods.dev/badge/skills/dailybothq/deepworkplan-skill/setup.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 | $0.00180 | $0.06046 |
| Opus 5.5 | $0.00072 | $0.02418 |
| Sonnet 5.5 | $0.00036 | $0.01209 |
| Haiku 4.5 | $0.00018 | $0.00605 |
Grade A, and why
ai-diff-reviewer-setup 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 — 531 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Diff Reviewer — Setup Wizard (sub-skill)
Companion to the ai-diff-reviewer skill. Where the parent
runs the review and generate-extension
tailors the prompt, this sub-skill bootstraps the GitHub Action
itself — walks the developer through the ~6 key decisions and writes
a working .github/workflows/pr-review.yml tailored to those choices.
Also doubles as the reference manual for every action.yml input:
if a developer asks any coding agent "what does strictness do?" or
"how do I run only when a label is added?", the agent can read
reference.md in this directory and answer without
opening the source.
When it fires
Explicit triggers (recommended):
- "Set up AI Diff Reviewer for this repo"
- "Configure the reviewer action"
- "Install the AI Diff Reviewer GitHub Action"
- "Help me create the pr-review workflow"
- "How do I add AI Diff Reviewer to this project?"
The parent ai-diff-reviewer skill may also route here
automatically when a review-flow request activates on a repo that
clearly has no .github/workflows/pr-review.yml (opt-in — future
enhancement; not the default today).
Step 0 — Trust boundary
This skill writes exactly two categories of files, both with explicit developer consent:
.github/workflows/pr-review.yml— the tailored workflow after all six questions are answered. If a file already exists at that path, the skill ASKS before overwriting (offers to write topr-review-new.ymlalongside for review)..review/extension.md— only if the developer says yes to the optional Step 5 handoff, which invokes thegenerate-extensionsub-skill.
It does not:
- Commit anything, push anything, or open a PR — the developer stages and commits themselves.
- Touch GitHub Secrets — they're set once by the developer in the repo's Settings UI (link surfaced in Step 4).
- Modify existing unrelated workflows in
.github/workflows/. - Call the LLM provider directly or send data off the machine.
What ships with it
1 file 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 afd87147fc88
- 4d ago Changed 4364750b12dd
- 5d ago Changed 9cbcf9b8d064
- 7d ago Changed 39b764f73960
- 10d ago Changed 469e31b5ee92
- 18d ago Changed cb31cb07aaa4
- 21d ago Changed 99c2f7b9ed7b
- 29d ago Changed · +64 lines b2bab94073d8
- 1mo ago Changed · +3 lines b9033f0d6273
- 1mo ago First seen · 464 lines · 180 tokens per session scan A 584ae1b650f8
ai-diff-reviewer-setup is a skill published in the GitHub repository DailybotHQ/deepworkplan-skill (23 stars, last pushed 3d ago), licensed MIT. It adds 180 tokens to every session and 6,046 once invoked, about $0.0007 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
loki-mode
An autonomous software factory that knows what it is supposed to deliver, and proves it did. Use when the user says Loki Mode or asks to build, fix or verify software autonomously.
checkpoint-mode
Pause for review every N tasks - selective autonomy pattern.
loki-mode
Launch Loki Mode autonomous SDLC agent. Handles PRD-to-deployment with minimal human intervention. Invoke for multi-phase development tasks, bug fixing campaigns, or full product builds.
prompt-optimization
Applies prompt repetition to improve accuracy for non-reasoning LLMs.
green-prs
Inspect and prepare the selected PR queue against its exact current base, repair authorized defects with contributor credit, and report full versus partial validation. Use for maintainer pre-greening; merging requires separate owner authorization and the shared merge gates.
gsd-ns-review
quality gates | code review debug audit security eval ui.