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 Liberty91LTD/cti-skills --skill devils-advocacygit clone --depth 1 https://github.com/Liberty91LTD/cti-skillsWrote 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/liberty91ltd/cti-skills/devils-advocacy)<a href="https://agentmods.dev/skills/liberty91ltd/cti-skills/devils-advocacy"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/devils-advocacy/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/liberty91ltd/cti-skills/devils-advocacy"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/devils-advocacy.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 | $0.00095 | $0.00813 |
| Opus 5.5 | $0.00038 | $0.00325 |
| Sonnet 5.5 | $0.00019 | $0.00163 |
| Haiku 4.5 | $0.00010 | $0.00081 |
Grade A, and why
devils-advocacy 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Devil's Advocacy
A contrarian technique from the CIA Tradecraft Primer. It takes the team's own lead judgment as its input and argues that the judgment is wrong. Its output is a rebuttal.
It is not Red Team Analysis. Red teaming is an imaginative technique: it reasons as the adversary would, from the adversary's position and constraints, and produces adversary courses of action. This pack does not have a Red Team Analysis skill. Until version 2.0 this skill carried that name.
When consensus is strong, this technique deliberately argues the opposing position. The goal is not to be contrarian for its own sake — it's to find genuine weaknesses in the prevailing analysis before they become blind spots.
When to Use
- Consensus is strong and unchallenged
- High-stakes assessment (wrong conclusion = significant harm)
- Analysis has been produced quickly under pressure
- The same team that collected also analysed (potential tunnel vision)
- Before publishing a product that will drive significant decisions
Procedure
Step 1: State the Prevailing Judgment
Write the current analytical consensus clearly and completely. Where the judgment rests on graded evidence from /quality-of-information-check, take the claim table with it: the weakest load-bearing claim is the first place to press.
Step 2: Argue Against It (With Maximum Effort)
Deliberately and rigorously construct the best possible case AGAINST the prevailing judgment:
- What evidence is being overweighted?
- What alternative explanations exist for the same evidence?
- What evidence has been ignored or underweighted?
- What assumptions are vulnerable? (cross-reference with key-assumptions-check)
- What would a sophisticated adversary do to make us believe the prevailing judgment?
- What historical cases looked similar but turned out differently?
Step 3: Assess the Opposing Case
Honestly evaluate:
- Are any of the opposing arguments compelling enough to change the judgment?
- Do they warrant lowering the confidence level?
- Do they identify intelligence gaps that should be filled?
- Do they suggest alternative hypotheses that should be tracked?
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 · 83 lines · 95 tokens per session scan A 94be78562c6e
devils-advocacy is a skill published in the GitHub repository Liberty91LTD/cti-skills (36 stars, last pushed 4d ago), licensed MIT. It adds 95 tokens to every session and 813 once invoked, about $0.0004 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 2026-10-01.
Other skills, from other repositories
analyzing-campaign-attribution-evidence
Systematically evaluate cyber-campaign evidence to attribute an operation to a threat actor, using the Diamond Model and Analysis of Competing Hypotheses (ACH) to weigh infrastructure overlaps, TTP consistency, malware code similarity, and timing/language artifacts into confidence-weighted attribution assessments. Use…
analyzing-threat-actor-ttps-with-mitre-attack
MITRE ATT&CK is a globally-accessible knowledge base of adversary tactics, techniques, and procedures (TTPs) based on real-world observations. This skill covers systematically mapping threat actor beh.
analyzing-threat-landscape-with-misp
Analyze the threat landscape using MISP (Malware Information Sharing Platform) by querying event statistics, attribute distributions, threat actor galaxy clusters, and tag trends over time. Uses PyMISP to pull event data, compute IOC type breakdowns, identify top threat actors and malware families, and generate threat…
analyzing-campaign-attribution-evidence
Use when campaign attribution analysis involves systematically evaluating evidence to determine which threat actor or group is responsible for a cyber operation. This skill covers collecting and weighting attr.
prompt-injection-auditor
Security audit of LLM system prompts, agent instruction files (SKILL.md, AGENTS.md, CLAUDE.md), and agent configurations against prompt injection attacks. Use when the user wants to (1) audit or harden a system prompt or agent instructions against prompt injection, (2) review an agent skill or system prompt for…
analyzing-campaign-attribution-evidence
Campaign attribution analysis involves systematically evaluating evidence to determine which threat actor or group is responsible for a cyber operation. This skill covers collecting and weighting attr.