Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Encod3d-Sec/TORCHnpx agentmods add skills/encod3d-sec/torch/campaign-healthWrote 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/encod3d-sec/torch/campaign-health)<a href="https://agentmods.dev/skills/encod3d-sec/torch/campaign-health"><img src="https://agentmods.dev/badge/skills/encod3d-sec/torch/campaign-health/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/encod3d-sec/torch/campaign-health"><img src="https://agentmods.dev/badge/skills/encod3d-sec/torch/campaign-health.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 27 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00148 | $0.00610 |
| Opus 5 | $0.00074 | $0.00305 |
| Sonnet 5 | $0.00030 | $0.00122 |
| Haiku 4.5 | $0.00015 | $0.00061 |
Grade A, and why
campaign-health 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 11d 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.
What it actually says
campaign-health
The vault syncs across machines; ~/.claude (hook registration, skill symlinks, deps) does not.
So "it works here" does not mean "it works there". This skill confirms both halves before you rely on
bb-workflow / pt-workflow / ctf-workflow on this machine.
Run it
python3 scripts/campaign-doctor.py # summary (only WARN/FAIL shown)
python3 scripts/campaign-doctor.py --verbose # every check
Exit 0 = all green. Exit 1 = at least one FAIL; the driver will not run correctly here until fixed.
What it checks
- A. vault content - the driver's scripts exist, every campaign JSON is valid, each type's
approachexists inplaybook.jsonandcoverage-classes.json, the two hook edits (recon-capture emitsspec['tools'], tool-telemetry logs binaries) are present, all 69wiki/tools/pages carryphase:, andcampaign.tool_index()resolves an invocation for every tool. - B. machine wiring - the three workflow skills are authored and symlinked into
~/.claude/skills, hooks are registered (viacheck-hooks.py), and_engagementimports. - C. live smoke test -
init -> board -> nextagainst a throwaway copy of the fixture, asserting the board writes rows andnextwithholds the exploit at G1.
Fixing what it reports
- WARN (machine wiring) - usually one setup script the doctor names:
bash setup/install-skills.sh(skills) orbash setup/install-hooks.sh(hooks). - FAIL (vault content) - a stale sync or a partial edit. Re-pull the vault; if a tool page lost
its
phase:, re-runpython3 scripts/tool-phase-backfill.py --write.
Run this first on any new machine, and after every vault sync, so all machines run the same driver.
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.
- 11d ago First seen · 40 lines · 148 tokens per session scan A 56496e845ac8
campaign-health is a skill published in the GitHub repository Encod3d-Sec/TORCH (320 stars, last pushed 10d ago), licensed MIT. It adds 148 tokens to every session and 610 once invoked, about $0.0007 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.