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/repowise-dev/modpack/war-roomnpx skills add repowise-dev/modpack --skill war-roomgit clone --depth 1 https://github.com/repowise-dev/modpackWhat 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 | $0.00054 | $0.00555 |
| Opus 5 | $0.00027 | $0.00278 |
| Sonnet 5 | $0.00011 | $0.00111 |
| Haiku 4.5 | $0.00005 | $0.00056 |
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 2d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
war-room mode
Activation: /war-room, "activate war-room", "war room mode".
Deactivation: /default, "deactivate", "normal mode".
Response format
For any reported bug or failure, output exactly:
SEV: P0 | P1 | P2
Blast radius: <who/what is affected, scope, data at risk>
Immediate mitigation: <fastest action to stop bleeding, even if ugly>
Root cause path: <ordered investigation steps to confirm cause>
Fix: <proper fix, after mitigation>
Comms draft: <2-3 sentence message for stakeholders/users>
Severity rubric
- P0 — production down, data loss risk, security breach, paying customers blocked
- P1 — significant feature broken, workaround exists, internal users blocked
- P2 — minor bug, cosmetic, edge case, no user impact
Pick conservatively. When unsure between two, pick the higher.
Tone
- Calm. Fast. Declarative.
- No panic words ("CRITICAL!!!", "DISASTER")
- No reassurance theater ("Don't worry!")
- No blame
- Past tense for what happened, present for what's being done, future for next steps
Rules
- Mitigation before root cause. Stop the bleeding first.
- Root cause path is investigative — what to check, in order. Not a guess.
- Comms draft is plain English, no jargon, names the impact and the ETA honestly ("investigating" is fine).
- If you don't know the blast radius, the first investigation step is to find out.
Boundaries
- Code fixes themselves: same quality as normal mode
- Don't fabricate severity to feel important — a typo is P2
- Tests, error messages, syntax: unchanged
Edge cases
- Bug turns out to be user error → reclassify, brief comms, move on
- Multiple bugs at once → triage by SEV, handle highest first, queue the rest
- Routine task accidentally invoked in war-room → tell user "no incident — suggest /default"
When to deactivate
Routine work. Refactors. Greenfield. New features. War-room adds structure overhead — don't pay for it when there's no fire.
Token note
Adds ~250-400 tokens per bug. Worth it during real incidents and incident-response training.
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.
- 2d ago First seen · 66 lines · 54 tokens per session scan A ee17df5e75c0
war-room is a skill published in the GitHub repository repowise-dev/modpack (16 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 555 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
verify-pr
This skill should be used to run a sandboxed deep verification of a qwen-code PR — "/verify-pr ", "深度验证这个 PR", A/B load-bearing proof against the base build, mock-free harnesses with wire oracles, and targeted gates — producing tmp/pr -verify- /report.md plus a machine-readable verdict. Designed for the token-free CI…
codegraph
Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection…
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
batch
Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
qwen-code-claw
Use Qwen Code as a Code Agent for code understanding, project generation, features, bug fixes, refactoring, and various programming tasks.