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 intent-driven-dev/intent-driven-template --skill adversarial-authoringgit clone --depth 1 https://github.com/intent-driven-dev/intent-driven-templateWrote 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/intent-driven-dev/intent-driven-template/adversarial-authoring)<a href="https://agentmods.dev/skills/intent-driven-dev/intent-driven-template/adversarial-authoring"><img src="https://agentmods.dev/badge/skills/intent-driven-dev/intent-driven-template/adversarial-authoring/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/intent-driven-dev/intent-driven-template/adversarial-authoring"><img src="https://agentmods.dev/badge/skills/intent-driven-dev/intent-driven-template/adversarial-authoring.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 | $0.00065 | $0.00839 |
| Opus 5.5 | $0.00026 | $0.00336 |
| Sonnet 5.5 | $0.00013 | $0.00168 |
| Haiku 4.5 | $0.00006 | $0.00084 |
Grade A, and why
adversarial-authoring 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial Authoring
Use this skill when an artifact rule, user request, or instruction says to use adversarial authoring, a model council, cross-model review, or a mixture of models.
The goal is to reduce single-perspective bias by having one configured subagent author the work and another configured subagent challenge it before the primary agent writes the final artifact.
Required Workflow
- Identify the artifact or task being authored, including its target output path.
- Gather the full task context before calling subagents:
- User request
- Relevant OpenSpec instruction JSON
- Artifact template
- Project context
- Artifact-specific rules
- Dependency artifacts already completed
- Start the authoring round with the
adversarial-authorsubagent. - Send the author draft and the original task context to the
adversarial-reviewersubagent. - Reconcile the review yourself as the primary agent:
- Accept corrections that improve correctness, clarity, requirements coverage, or risk handling.
- Reject suggestions that conflict with the user request, artifact template, OpenSpec instructions, or project rules.
- Ask the user only if the disagreement changes product intent or cannot be resolved from available context.
- Write the final artifact to the requested output path.
- Write council notes beside the artifact using the naming convention below.
Subagents
Use these hard-coded opencode subagents:
adversarial-author: authors the initial draft.adversarial-reviewer: reviews and challenges the draft.
The specific model providers are intentionally defined only in the agent files, so changing model families only requires updating each agent's model frontmatter.
Do not substitute other agents unless the user explicitly requests it.
Council Notes
For every artifact authored through this skill, create or update a sibling council-notes file.
Naming convention:
proposal.md->proposal.council.mddesign.md->design.council.mdtasks.md->tasks.council.mdspec.md->spec.council.md
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 · 88 lines · 65 tokens per session scan A c62e94322478
adversarial-authoring is a skill published in the GitHub repository intent-driven-dev/intent-driven-template (177 stars, last pushed 5d ago), licensed MIT. It adds 65 tokens to every session and 839 once invoked, about $0.0003 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
seats-aero
Search award flight availability across 27 mileage programs via Seats.aero Partner API. Find cheapest award flights, compare programs, and get booking links.
round-the-world
Round-the-world, Circle Pacific, and distance-based award products across alliances. Covers Star Alliance RTW, oneworld Explorer, Lufthansa M&M, Qantas, Cathay, JAL, Aeroplan, and Iberia charts.
scandinavia-transit
Search trains, buses, and ferries in Norway (Entur), Sweden (ResRobot), and Denmark (Rejseplanen). Intra-Scandinavia ground transport with schedules and Danish fare pricing.
southwest
Search Southwest Airlines fares and points pricing via Patchright browser automation. SW is not in any GDS or API. Covers all fare classes, Companion Pass value, and fare drop monitoring.
status-match
Status match and status challenge rules for airlines and hotels. Covers free direct matches, paid concierge via statusmatch.com with fees, card-granted status, and critical lifetime/once-per-N-years restrictions that make wasted matches expensive.
ticketsatwork
Search TicketsAtWork (EBG corporate perks) for hotels, theme park tickets, attractions, and rental cars via Patchright. Often beats portals by 10-30%. Use when comparing hotel or ticket prices for a trip.