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 D-Robotics/moss --skill patch-disciplinegit clone --depth 1 https://github.com/D-Robotics/mossWrote 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/d-robotics/moss/patch-discipline)<a href="https://agentmods.dev/skills/d-robotics/moss/patch-discipline"><img src="https://agentmods.dev/badge/skills/d-robotics/moss/patch-discipline/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/d-robotics/moss/patch-discipline"><img src="https://agentmods.dev/badge/skills/d-robotics/moss/patch-discipline.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 | $0.00026 | $0.00238 |
| Opus 5.5 | $0.00010 | $0.00095 |
| Sonnet 5.5 | $0.00005 | $0.00048 |
| Haiku 4.5 | $0.00003 | $0.00024 |
Grade A, and why
patch-discipline scanned grade A with 1 finding 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 23d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
4. All subprocesses go through `runProcess` / `spawnProcess` from `src/utils/run-process.ts`; tool paths must not use execFileSync/execSync. What it actually says
Patch discipline for moss
- Read the real source before editing. Never guess behavior from file names.
- Make the minimal change that fixes the problem. Match surrounding style; do not refactor neighbors in the same patch.
- Every user-facing success message must come from a real probe, exit code, or post-condition — never a fixed string.
- All subprocesses go through
runProcess/spawnProcessfromsrc/utils/run-process.ts; tool paths must not use execFileSync/execSync. - New tools must declare
metadata.sideEffectClass(readonly vs mutating drives approval). - After a logic change:
npm run buildthen run the touched spec (npm run test:filter -- --filter <module>). A bug fix needs a red-then-green regression spec. - Errors crossing tool/provider/CLI boundaries become
MossErrorwith the original cause preserved.
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.
- 23d ago First seen · 16 lines · 26 tokens per session scan A 0d2454b45f19
patch-discipline is a skill published in the GitHub repository D-Robotics/moss (143 stars, last pushed 5d ago), licensed MIT. It adds 26 tokens to every session and 238 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-01.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…