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/sistema2d/framecode-vibework/systematic-debuggingnpx skills add Sistema2D/FrameCode-VibeWork --skill systematic-debugginggit clone --depth 1 https://github.com/Sistema2D/FrameCode-VibeWorkWhat 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 | $0.00016 | $0.00487 |
| Opus 5 | $0.00008 | $0.00244 |
| Sonnet 5 | $0.00003 | $0.00097 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
systematic-debugging 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic debugging
Purpose
Find the smallest evidence-supported cause of a failure and distinguish diagnosis from implementation authorization.
Use conditions
Use for reproducible defects, crashes, failed checks, unexpected behavior, or inconsistent runtime state. For a question limited to diagnosis, do not apply a fix. For an authorized fix, follow the active plan and changelog contract.
Non-responsibilities
- unrelated refactoring or speculative cleanup;
- suppressing symptoms without explaining the cause;
- publishing secrets, credentials, or unnecessary raw logs;
- treating an unverified hypothesis as a finding.
Inputs
Expected behavior, observed behavior, environment, reproduction steps, logs or stack traces, recent changes, and the narrowest relevant source and test files.
Procedure
- Reproduce the problem or state why reproduction is currently impossible.
- Capture the exact symptom, environment, and smallest failing case.
- Form one ranked hypothesis tied to concrete evidence.
- Design a check that can disprove that hypothesis.
- Run the check and update the hypothesis from the result.
- Repeat until the cause is supported or the investigation is explicitly inconclusive.
- If a fix is authorized, add or identify a regression check, apply the minimal change, remove temporary instrumentation, and rerun affected validation.
- Promote durable incident learning to a troubleshooting record when recurrence, severity, or operational value justifies it.
Required output
Symptom, reproduction status, evidence, tested hypotheses, supported root cause or remaining uncertainty, affected scope, and validation results. If code changed, link the active plan and changelog entry.
Validation
The original failure is reproduced before the fix when feasible, the causal check changes as predicted, the regression check passes afterward, and unrelated validation has not regressed.
Exit criteria
Exit when the cause is supported and the authorized fix is validated, or when the remaining blocker and next evidence needed are recorded without presenting speculation as resolution.
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 · 60 lines · 16 tokens per session scan A 18b4a990ebbf
systematic-debugging is a skill published in the GitHub repository Sistema2D/FrameCode-VibeWork (21 stars, last pushed 11d ago), licensed Apache-2.0. It adds 16 tokens to every session and 487 once invoked, about $0.0001 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
evaluate-pattern-adoption
Run or plan this repository's pattern-adoption evidence evaluation locally with signed-in Codex agents. Use when asked to refresh stale evidence, assess stable or exploratory patterns, evaluate one or all catalog patterns, discover possible new patterns, or prepare a reviewable evidence PR without model-backed GitHub…
traceability-gate
Enforces parent-link lineage across requirement layers.
wendao
Internal guardian skill for creating and editing Wendao DocOS documentation.
release
Cut a sim-use release end-to-end. Use when the user runs /release or asks to "ship a release", "publish a version", "cut a release", or "release to homebrew". Drives scripts/local-release.sh; never reimplement its build/sign/tarball logic.
browser_cdp
通过 Chrome DevTools Protocol (CDP) 连接已运行的浏览器,或扫描本机 CDP 端口,用于远程调试与多工具共享浏览器实例。.
silicon-throne
硅基圣座总控核心,以神谕式统御把零散任务压成 末将-first 之文明工程.