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 Langerrr/zforge --skill debuggit clone --depth 1 https://github.com/Langerrr/zforgeWrote 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/langerrr/zforge/debug)<a href="https://agentmods.dev/skills/langerrr/zforge/debug"><img src="https://agentmods.dev/badge/skills/langerrr/zforge/debug/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/langerrr/zforge/debug"><img src="https://agentmods.dev/badge/skills/langerrr/zforge/debug.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 | $0.00020 | $0.00536 |
| Opus 5.5 | $0.00008 | $0.00214 |
| Sonnet 5.5 | $0.00004 | $0.00107 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
debug 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 1mo 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugging Router
A concrete failure — a broken test, a reproducible bug, a failing deploy. This skill owns no debugging opinion of its own; it names which methodology applies and in what order, because the failure mode is applying one of them and skipping the rest.
Not for open-ended exploration ("this feels wrong"). That is $compound-engineering:ce-ideate territory.
Sequence
1. $superpowers:systematic-debugging — start here when installed.
Investigation discipline comes before any fix, including when the cause seems obvious. When Superpowers is unavailable, use the host's equivalent systematic-debugging workflow; do not skip the investigation step.
2. $compound-engineering:ce-debug — add when installed.
Its hypothesis-and-prediction gate goes before any code change: state what you believe is wrong and what you expect to see if you are right, then check. Without Compound Engineering, apply that same hypothesis-and-prediction gate directly. A fix applied without a failed prediction is a guess that happened to be typed confidently.
3. $zforge:async-reasoning — add when the failure involves timing.
Async state, race conditions, cache invalidation, init order, stale reads, write-then-read gaps within one component.
4. $distributed-architect:dist-debug — add when that compatible plugin is installed and the failure crosses a boundary.
Cross-service, cross-process, distributed races. Backward tracing from the symptom to the boundary where the cause lives. Check the project's topology file first if it has one.
While debugging a planned feature
If the failure is in a feature with a zforge directory, the ledger is evidence:
decision_review.mdmay already contain the decision that caused this.- An open standing flag may already name this defect class — a bug in the gap a flag describes is a flag being discharged the expensive way.
- The phase's
## Evidence Requiredshows what was never verified, which is usually where to look first.
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.
- 1mo ago First seen · 42 lines · 20 tokens per session scan A 86544ea34bda
debug is a skill published in the GitHub repository Langerrr/zforge (10 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 536 once invoked, about $0.0001 per session on Opus 5.5. 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
trace-incident
Traces a production symptom to its cause and produces a minimal hotfix plan at .workflow/incident- /sdd.json with a timeline. Use when something is broken in production now.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
roslyn-query
Query .NET/C# codebases using Roslyn AST analysis via dotnet run file. Use for tracing data flow, auditing API usage, finding pattern violations, or ad-hoc codebase queries.
apex-review
Cross-cutting review of recent work — catches gaps between specialists. Use when asked to "review what we built", "check the work", "pre-launch review", or after completing a significant chunk of work.
shipyard-debugging
Investigates root cause systematically before any fix is proposed. Use when encountering any bug, test failure, unexpected behavior, or error message. Also use for tracebacks, exceptions, "not working" complaints, build failures, performance problems, or integration issues, and whenever the next step would be to…
codebase-hygiene
Two-mode skill: (1) find semantic duplicates — functions doing the same thing under different names, invisible to copy-paste detectors; (2) deepen shallow modules — thin wrappers and pass-through layers that spread complexity. Advisory and read-only; changes route through BUILD with full gates.