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 arbazkhan971/godmode --skill debuggit clone --depth 1 https://github.com/arbazkhan971/godmodeWrote 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/arbazkhan971/godmode/debug)<a href="https://agentmods.dev/skills/arbazkhan971/godmode/debug"><img src="https://agentmods.dev/badge/skills/arbazkhan971/godmode/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/arbazkhan971/godmode/debug"><img src="https://agentmods.dev/badge/skills/arbazkhan971/godmode/debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Tool Misuse · line 96 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00018 | $0.01831 |
| Opus 5.5 | $0.00007 | $0.00732 |
| Sonnet 5.5 | $0.00004 | $0.00366 |
| Haiku 4.5 | $0.00002 | $0.00183 |
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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Activate When
/godmode:debug, "why is this happening?", "this doesn't work"
Lessons Integration
Before investigation: read .godmode/lessons.md for known root causes and debugging shortcuts.
After session: append lessons about root cause patterns discovered.
The Loop
failing_count = run_tests() # test_cmd (from stack detection), count failures
current_iteration = 0
skipped = 0
WHILE failing_count > 0 AND skipped < 3:
current_iteration += 1
bug = pick_highest_severity(remaining_bugs)
technique_index = 0
techniques = [stack_trace, git_bisect, state_inspection, binary_search]
# 1. REPRODUCE — run failing command 3x. Consistent failure = real bug. Intermittent = add to flaky list.
# 2. SELECT TECHNIQUE (max 5 min each):
Stack trace → Trace Analysis | "Used to work" → `git bisect` | Regression → `git log -20`
Intermittent/Wrong results → State Inspection | Unknown → Binary Search (eliminate half)
# 3. INVESTIGATE — insert print/log at suspect file:line. Log: variable name=value, caller, actual vs expected.
# 4. PROVE — state: "Bug is at {file}:{line} because {variable}={actual}, expected {expected}. Reproduce: {cmd}."
Chain: Symptom → Why? → Why? → Root cause → Fix (file:line + diff). Min 3 'why's.
# Root cause found → KEEP (fix or hand off)
# Root cause NOT found → try next technique (step 2)
# All techniques exhausted → DISCARD bug (skip++), log reason_stuck + root_cause_unknown
# 5. FIX OR HAND OFF — see Fix Handoff Protocol below
# 6. VERIFY — re-run failing test. Then run full suite to check for regressions.
# 7. APPEND .godmode/debug-findings.tsv: iteration, bug_id, symptom, root_cause, file:line, fix_commit, status(fixed/skipped), reason_stuck
# 8. STATUS every 3: "{found} found, {failing_count} remaining, {skipped} skipped"
failing_count = run_tests()
IF skipped >= 3: STOP, report partial results
Stuck Criteria
IF stuck >3 iterations on same bug:
→ Discard bug, move to next
→ Log: bug_id, reason_stuck, root_cause_unknown, skipped=true
→ Max skipped bugs: 3. After 3 skipped → stop, report partial
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 163 lines · 18 tokens per session scan A 7e0038619348
debug is a skill published in the GitHub repository arbazkhan971/godmode (27 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,831 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 2026-08-30.
Other skills, from other repositories
deliver-edge-cases
Documents edge cases, error states, boundary conditions, race conditions, and recovery paths for a feature - the systematic catalog of what can go wrong and the failure modes to design for. Use during specification to map the failure surface and ensure comprehensive coverage, or during QA planning to identify boundary…
om-fix
Implements the minimal code change identified by the om-root-cause step, adds regression tests, and runs the configured validation gate. Claims the tracker issue at start (assignee + in-progress label + claim comment) so concurrent automation backs off. Does not commit, push, or open a PR — that is the om-open-pr…
squid-architecture-review
Periodic architectural sweep — reads existing ADRs, maps modules/dependencies/layering, and reports up to 10 prioritised findings shaped as refactor proposals /squid-refactor can consume directly.
analyze
Analyzes code quality, complexity, patterns across codebase. Triggers: quality report, hotspot scan, code analysis, architecture signal.
ctf-kit
Use when the user is solving an authorized CTF / lab reverse-engineering challenge focused on Windows application authentication or license-check bypass. Guides triage → static analysis → dynamic experiment planning → bypass verification, with strong evidence discipline and VM safety boundaries. NOT for real-world…
memory-lint
Use when the user wants to lint a Claude Code memory directory (/.claude/memory or custom path) for index inconsistency, broken cross-links, stale project state, duplicate / conflicting feedback rules, naming violations, frontmatter gaps, and oversized files. Phase 1 is a read-only scan and report. Phase 2 applies…