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 agentmods add skills/melodic-software/claude-code-plugins/devils-advocatenpx skills add melodic-software/claude-code-plugins --skill devils-advocategit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWrote 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/melodic-software/claude-code-plugins/devils-advocate)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/devils-advocate"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/devils-advocate.svg" alt="Measured on agentmods" 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 | $0.00164 | $0.04218 |
| Opus 5 | $0.00082 | $0.02109 |
| Sonnet 5 | $0.00033 | $0.00844 |
| Haiku 4.5 | $0.00016 | $0.00422 |
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 yesterday.
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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-computed context
Current branch: !git branch --show-current 2>/dev/null || echo "unknown"
Recent commits: !git log --oneline -5 2>/dev/null || echo "no commits"
Variables
Arguments: $ARGUMENTS
Purpose
Plans fail for predictable reasons: unchecked assumptions, undiscovered bugs in dependencies, missing extensibility, no drift detection, no graceful degradation. This skill systematically finds these problems BEFORE implementation begins.
Not a rubber stamp. Find real issues that would cause rework, not generic warnings. Every finding must be backed by evidence. A specific bug number, doc reference, code path, or logical argument. "This might break" without evidence is not a finding.
The same discipline runs against the status quo. An incumbent tool, library, or approach already in place is a decision too, and "we already use it" is evidence of what is, never proof it still fits. The incumbent mode stress-tests that choice, naming the problem the incumbent actually solves, surveying alternatives, and asking whether a better fit exists now, before a plan commits to keeping or replacing it.
Fresh-context requirement
This stress-test runs from a fresh pair of eyes, and dispatches to a fresh-context sub-agent in two cases:
- Plan-review mode. If the plan under review was produced in THIS context/session, the producing context shares the assumptions that created the plan's blind spots and drifts toward approving its own work; dispatch the stress-test to a fresh-context sub-agent. When you were invoked on an artifact this context did not author (a file, a plan from another session, a diff), you are already the fresh pair of eyes. Proceed directly.
incumbentmode. Always dispatch. The incumbent lives in the current codebase, so any read of it you already hold is a digest; a first-hand exploration is what forms an independent view. The sub-agent invokes/discovery:explorevia the Skill tool (if installed, else explores directly) on the incumbent itself (Alternatives Sweep, Step 1).
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.
- yesterday First seen · 228 lines · 164 tokens per session scan A 8dcc1eb155c5
devils-advocate is a skill published in the GitHub repository melodic-software/claude-code-plugins (15 stars, last pushed today), licensed MIT. It adds 164 tokens to every session and 4,218 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
parallel-orchestrator
Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue lists). Triggers: parallel, orchestrator, worktrees…
parallel-worker
Execute focused implementation tasks in a parallel workflow. Use when: working on assigned files in a worktree, making checkpoint commits, signaling dependencies or blockers, completing orchestrator-assigned tasks. Triggers: worker, checkpoint, worktree, assigned scope, commit prefix, parallel task.
build-priority-queue
For ordered processing: A search, Dijkstra, event simulation, task scheduling. Efficient min/max extraction with heap-based queue.
catch-expected-errors
For iteration with errors: catch exceptions during exploration, skip invalid cases, continue to next attempt.
compose-small-helpers
For complex behavior: build from tiny functions, chain transformations, make code read like a pipeline of operations.
count-combinations
For probability and counting: permutations, combinations, sample spaces, Monte Carlo simulation, brute-force enumeration, card/dice problems.