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 Ovid/paad --skill paad-helpgit clone --depth 1 https://github.com/Ovid/paadWrote 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/ovid/paad/paad-help)<a href="https://agentmods.dev/skills/ovid/paad/paad-help"><img src="https://agentmods.dev/badge/skills/ovid/paad/paad-help/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/ovid/paad/paad-help"><img src="https://agentmods.dev/badge/skills/ovid/paad/paad-help.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00071 | $0.07184 |
| Opus 5 | $0.00036 | $0.03592 |
| Sonnet 5 | $0.00014 | $0.01437 |
| Haiku 4.5 | $0.00007 | $0.00718 |
Grade A, and why
paad-help 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 9d 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 — 730 lines — stays where its author put it; the contents beside it link to each section on GitHub.
On invocation: announce "Running paad:paad-help v1.31.0" before anything else.
paad Help
Show help for paad skills. If $ARGUMENTS matches a skill name, show detailed help for that skill. Otherwise, show the overview.
Arguments
/paad-help— show all available skills/paad-help vibe— show detailed help for a specific skill/paad-help agentic-review— skill names with hyphens work too
Behavior
If $ARGUMENTS is provided and matches a skill name (with or without the paad: prefix), show the detailed help for that skill only. If the argument doesn't match any skill, say "Unknown skill: [name]. Available skills:" and show the overview.
Do NOT read files or run commands. All help text is below.
Common Mistakes
| Mistake | What to do instead |
|---|---|
| Paraphrasing or summarizing the help text | Display the blocks verbatim. Arguments and output paths are exact; a paraphrase invents flags that don't exist. |
| Answering for a skill not listed here | If it isn't below, it isn't a paad skill. Say "Unknown skill: [name]" and show the overview. |
| Running the skill the user asked about | They asked what it does, not for it to happen. Show the help and stop. |
Overview (no arguments)
When showing the overview, display exactly this:
paad — Engineering-driven AI.
Use your engineering excellence — the one thing AI reliably skips.
Available skills:
/agentic-a11y [path] Accessibility audit (web, mobile, desktop, CLI, games)
/agentic-architecture [path...] Multi-agent architecture analysis (strengths & flaws)
/fix-architecture [report] Fix architectural flaws from an analysis report
/agentic-review [base-branch] [path] Multi-agent code review of current branch (bug hunting)
/alignment [files...] Requirements-to-tasks alignment + TDD rewrite
/makefile Create or update a Makefile with standard targets
/pushback [document] Spec/PRD/doc critic (finds issues before you build)
/vibe [task description] Safe vibe coding with TDD guardrails
Experimental — may change or be withdrawn in any release, including patches:
/agentic-dedup [scope] Find semantic duplication (same meaning, different code)
/agentic-owasp [scope] Security review against the OWASP Top 10:2025
/handoff [save|resume] Hand this session's work to a fresh session, in writing
/rethink [what to re-examine] Verify the premises under options already on the table
/test-roadmap Plan and build a test suite that catches real regressions
Picking between them:
Want structural flaws found? agentic-architecture (diagnoses, does not fix)
Want them fixed? fix-architecture (needs a report first)
Want bugs in a branch? agentic-review (a diff, not the codebase)
Want accessibility barriers? agentic-a11y (not general correctness)
Want duplicated logic found? agentic-dedup (experimental; reports,
never refactors)
Worried about security specifically? agentic-owasp (experimental; the OWASP
Top 10:2025, never exploits or fixes)
Have no tests, or tests you distrust? test-roadmap (experimental; the only
skill that writes and commits code)
Have one document, is it any good? pushback (a spec, a steering file, a
generated report)
Been handed options, are they sound? rethink (experimental; checks premises,
does not invent alternatives)
Out of context, work unfinished? handoff (experimental; writes a file for
a NEW session — /compact stays in this one)
Have a spec AND a plan, do they match? alignment (needs both; does not read code)
Making a small change? vibe (1-3 files, same module)
Change is clearly multi-module? write a plan, then alignment against it
Build is broken? none of these — makefile manages targets,
it does not debug builds
Run /paad-help <skill-name> for detailed help on a specific skill.
Invoking: the names above are slash commands on Claude Code. If your
assistant does not take them, ask for the skill by name ("run the pushback
skill"). If another plugin ships a skill with the same name, disambiguate with
the paad: prefix — /paad:vibe rather than /vibe.
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.
- 9d ago First seen · 730 lines · 71 tokens per session scan A b1e497ad947b
paad-help is a skill published in the GitHub repository Ovid/paad (111 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 7,184 once invoked, about $0.0004 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
nopua
A guidance skill for coding agents that promotes patient, thorough, self-directed work instead of fear or threats.
nopua-lite
NoPUA Lite — core wisdom in 1.5k tokens. Drives AI with trust and inner motivation instead of fear. Same Daoist philosophy, minimal footprint. For personal use and small-context models.
ccg-namespace
Isolate read-only CCG search, documentation discovery, and analysis by namespace. Use when working across multiple repositories or services, preventing cross-project graph leakage, federating supported reads, or traversing materialized cross-namespace references. Do not use for graph writes or scoped updates; the user…
wgm
Autonomous build skill that turns a rough request into working software through a relentless requirements interview (grill), a persistent plan, and a Ralph-style build loop (analyze → implement → validate → review → record). Use when the user runs /wgm, or asks to build, implement, prototype, or ship a feature or app…
rugged
Companion review skill that stress-tests a request, spec, plan, diff, or system against the operators and environment that will actually run it, not an idealized one. Runs a disciplined lifecycle (Triage -> Context -> Bottleneck decomposition -> Simplify -> Field test -> Verdict) and emits exactly one of three…
teach-me
Companion learning skill that makes a codebase legible fast. Surveys a repository, builds a cited map, runs a guided tour in dependency order, and finishes with a validated first change so the learner has actually moved the code. Use when the user runs /teach-me, or asks to learn, understand, onboard onto, get up to…