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 frankaging/lite-research-agents --skill war-roomgit clone --depth 1 https://github.com/frankaging/lite-research-agentsWrote 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/frankaging/lite-research-agents/war-room)<a href="https://agentmods.dev/skills/frankaging/lite-research-agents/war-room"><img src="https://agentmods.dev/badge/skills/frankaging/lite-research-agents/war-room/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/frankaging/lite-research-agents/war-room"><img src="https://agentmods.dev/badge/skills/frankaging/lite-research-agents/war-room.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 | $0.00040 | $0.02050 |
| Opus 5 | $0.00020 | $0.01025 |
| Sonnet 5 | $0.00008 | $0.00410 |
| Haiku 4.5 | $0.00004 | $0.00205 |
Grade A, and why
war-room 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- war-room — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
War Room Skill
A war room runs personas through a structured two-phase session:
-
Phase 1 — Ideation (5 rounds max): personas debate the research idea question by question. Ends early on consensus (all
[AGREE]or[PASS], no[OBJECT]) or two consecutive all-[PASS]rounds. Output:memory/war-room/idea-snapshot.md -
Phase 2 — Proposal (5 rounds max): personas collaboratively draft each proposal section. Output:
memory/war-room/proposal-draft.md
Configurations
Defined in skills/war-room/personas/agents.json under the configurations key.
| Name | Participants | Use when |
|---|---|---|
full |
Creative, Senior Prof, Young Faculty, Industry Liaison | Deep ideation, novel directions, full proposal needed |
1on1 |
Senior Professor, Young Faculty | Quick feasibility check, tight scope |
The configuration is specified in PROJECT.md frontmatter under war_room.configuration. Default: full.
Consensus Protocol
Every persona response must end with one of:
| Tag | Meaning |
|---|---|
[AGREE] |
I accept the current position |
[PASS] |
No strong view either way |
[OBJECT: reason] |
I reject — give specific reason |
Do not embed tags mid-response. They must be the final line.
Single-Agent Fallback (Codex / no subagent spawning)
If you cannot spawn subagents, run the same loop inline. For each persona turn:
- Print a clear header:
--- [Round N] <Persona Name> --- - Adopt that persona fully for your response — voice, stance, debate style, red lines.
- End with the consensus tag (
[AGREE],[PASS], or[OBJECT: reason]). - Return to moderator role between turns to write the log entry and check consensus.
Drift detection still applies: before each turn, re-read the persona definition and note whether your previous response for that persona drifted from their stance.
Playbook
Follow this sequence exactly. You are the moderator/orchestrator throughout.
What ships with it
6 files 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.
- 9d ago First seen · 201 lines · 40 tokens per session scan A 56c980f74795
war-room is a skill published in the GitHub repository frankaging/lite-research-agents (3 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 2,050 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
manage-tickets
Create, edit, search, transition, close, and triage Jira tickets via the Atlassian MCP. Use when asked to file a bug, request a feature, create a task, log a defect, search the backlog, triage findings into the tracker, edit ticket fields, transition status, or manage Jira work items. Also use when the user says…
vet-dependency
Measure a candidate library's real maintenance state and its behavior against the protocol, schema, or API version the project has already pinned, before taking it as a dependency. Covers any ecosystem (Go, npm, PyPI, Cargo, Maven) and any forge (GitHub, GitLab, Gitea). Use when deciding whether to adopt, replace, or…
compare-it
Produce structured architectural comparison documents that evaluate two tools, technologies, or solutions against weighted criteria. Use when asked to compare tools, evaluate alternatives, write a technology assessment, create a build-vs-buy analysis, or produce a recommendation report. Also use when someone says…
improve-self
Detect when a missing Agent Skill would have made the current task faster or more reliable, then scaffold a candidate SKILL.md for user review. Use after a non-trivial task when one of these signals fires: the same procedure repeated 3+ times, error recovery required inventing a workflow, the user corrected the…
log-changes
Use when asked to update the changelog, document version changes, prepare a release, or add entries for recent work, and when reviewing a diff or pull request that touches CHANGELOG.md. Produces concise user-facing CHANGELOG.md entries, follows Keep a Changelog and Semantic Versioning, and verifies that new bullets…
make-skill
Use when creating, improving, comparing, evaluating, reviewing or packaging Agent Skills following the agentskills.io specification. Also use when deciding whether a skill is the right solution vs MCP servers, Claude Rules Files, CLAUDE.md or AGENTS.md. Handles SKILL.md authoring, frontmatter optimization, description…