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 Effulgent-Point/paw --skill devils-advocategit clone --depth 1 https://github.com/Effulgent-Point/pawWrote 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/effulgent-point/paw/devils-advocate)<a href="https://agentmods.dev/skills/effulgent-point/paw/devils-advocate"><img src="https://agentmods.dev/badge/skills/effulgent-point/paw/devils-advocate/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/effulgent-point/paw/devils-advocate"><img src="https://agentmods.dev/badge/skills/effulgent-point/paw/devils-advocate.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 | $0.00000 | $0.00430 |
| Opus 5.5 | $0.00000 | $0.00172 |
| Sonnet 5.5 | $0.00000 | $0.00086 |
| Haiku 4.5 | $0.00000 | $0.00043 |
Grade A, and why
devils-advocate 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 1mo 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.
What it actually says
Devil's Advocate Skill
When to use: Reviewing any plan before commitment — architecture, implementation plan, migration strategy, design proposal.
Attack patterns
For every step in a plan, ask:
- What if it fails halfway? — is there a recovery path, or are you stuck in a broken state?
- What if the input is wrong? — garbage in, does it fail loudly or corrupt silently?
- What if this runs concurrently with other work? Race conditions? Conflicting writes?
- What if this needs to work at 10x scale? — does it still hold, or is there a hidden O(n^2)?
- What's the simplest version? — is this overengineered for the actual requirement?
Red flags to look for
- "For now" — means "forever" unless there's a ticket and a date
- "We'll fix later" — later never comes. If it matters, fix it now or accept the risk explicitly
- Hand-waved steps — "then we just deploy" / "the migration handles it" / "the API returns the data we need"
- Missing error paths — only the happy path is described
- Implicit assumptions — "users will have..." / "the data is always..."
The 6-month test
Would a new team member, reading this plan in 6 months with no context, understand:
- What was decided and why?
- What was explicitly NOT done and why?
- What could go wrong and what the mitigation is?
If not, the plan is underspecified.
Structuring concerns
- Blockers — must address before building. The plan doesn't work without this.
- Warnings — should address. Known risk if you don't.
- Notes — worth considering. Won't block but worth knowing.
Be specific. "This might have issues" is useless. "The batch job at step 3 has no timeout — if the API hangs, the job runs forever" is actionable.
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.
- 1mo ago First seen · 39 lines · 0 tokens per session scan A d14fb206d777
devils-advocate is a skill published in the GitHub repository Effulgent-Point/paw (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 430 tokens. 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 2026-08-31.
Other skills, from other repositories
wttr-weather
Weather via wttr.in GET (no key). Use for weather/forecast; prefer os.http.request.
jk
Manage Jenkins controllers with jk, including jobs, runs, logs, artifacts, credentials, nodes, queues, and plugins.
ground-state
Before starting any non-trivial implementation, run a pre-flight reconnaissance pass to triangulate git state, project infrastructure, and prior-session memory. Auto-assembles a verified grounding preamble — a session-scoped artifact the orchestrator pastes verbatim into every subsequent sub-agent brief — eliminating…
engineering-principles
Practical engineering judgement: smallest change, subtract before adding, data structures before logic, idempotent operations, migrate callers then delete. Use when designing, building, or reviewing changes.
financial-analysis
Financial figures done carefully: periods and fiscal calendars, units and currencies, reconciliation, magnitude sanity checks, sourced assumptions. Use for statements, budgets, pricing, and diligence numbers.
scheduling
Scheduling across time zones: confirm times in the attendee's own zone, use IANA zone names, mind DST edges, buffers and calendar etiquette. Use when booking meetings or calls with people in other zones.