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 optimizegit 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/optimize)<a href="https://agentmods.dev/skills/arbazkhan971/godmode/optimize"><img src="https://agentmods.dev/badge/skills/arbazkhan971/godmode/optimize/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/optimize"><img src="https://agentmods.dev/badge/skills/arbazkhan971/godmode/optimize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 121 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.
- high Tool Misuse · line 144 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 | $0.00019 | $0.01576 |
| Opus 5 | $0.00010 | $0.00788 |
| Sonnet 5 | $0.00004 | $0.00315 |
| Haiku 4.5 | $0.00002 | $0.00158 |
Grade A, and why
optimize 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 8d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Activate When
/godmode:optimize, "make faster", "improve", "optimize"
Setup (once)
Ask: Goal, Metric (cmd -> single number),
Direction (up/down), Scope (file globs).
Baseline
# Run metric_cmd 3 times, take median
metric_cmd; metric_cmd; metric_cmd
IF variance >5%: 10 runs, trim outliers, median of 8. If metric variance > 5% across 3 runs: consider Docker isolation for deterministic measurement. Log variance alongside metric in results.tsv. Commit baseline as iteration 0.
Guard vs Metric
METRIC: shell cmd -> single number (target)
GUARD: test_cmd && lint_cmd && build_cmd (must pass)
Change must BOTH improve metric AND pass guard.
Guard failure -> DISCARD (terminal, counts against
2-rework cap).
Session Resume
On start: check .godmode/session-state.json. If resuming (stop_reason is null), restore baseline/round/approach_history and skip to saved round.
After each iteration: atomically save state (round, baseline, current_best, last_kept_commit, consecutive_discards, approach_history, failure_classes) to .godmode/session-state.json.
On completion: set stop_reason in the state file.
Lessons Integration
Before IDEATE: read .godmode/lessons.md for optimization-specific insights.
After session: append lessons (e.g., "Metric X is I/O-bound, not CPU-bound" or "Table Y too small for index benefit").
The Loop
WHILE current_round < max_rounds:
1. REVIEW: in-scope files + results.tsv + git log
Read last 10 rows of optimize-failures.tsv before proposing next change. Avoid repeating the most common failure class.
Profile first: identify hotspot before changing.
IF bounded AND remaining < 3: exploit only.
2. HYPOTHESIZE: 3 independent untested changes
(algorithmic > caching > structural)
IF >5 consecutive discards: STUCK RECOVERY
3. DISPATCH 3 AGENTS (parallel, worktrees)
Each: ONE change -> commit -> guard -> 3x verify
Timeout: 5 min per agent. Exceeded -> kill+discard.
4. PICK WINNER: largest improvement
improved + guard pass -> cherry-pick, update baseline
improved + guard fail -> rework (max 2), else discard
no improvement -> discard all
5. LOG to .godmode/optimize-results.tsv
6. STATUS every 5 rounds.
Last 3 keeps <1% -> radical -> compound -> STOP
STOP: target | max rounds | diminishing | guard broken
What ships with it
3 files 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.
- 8d ago First seen · 162 lines · 19 tokens per session scan A 36ca5a2a5f3b
optimize is a skill published in the GitHub repository arbazkhan971/godmode (26 stars, last pushed 14d ago), licensed MIT. It adds 19 tokens to every session and 1,576 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 2026-09-03.
Other skills, from other repositories
node-zombie-guardian
Use when diagnosing stale or orphaned Node.js processes launched by VCO, auditing ownership/liveness, or safely simulating cleanup without touching external Node workloads.
architecture-optimization
Guided journey from a working codebase grown slow and tangled to one measurably fast, cleanly bounded, and readable. Orchestrates eight skills phase by phase - working-with-legacy-code, clean-architecture, software-design-philosophy, refactoring-patterns, system-design, ddia-systems, release-it, pragmatic-programmer …
code-cleanup
Detect stale TODOs, unused imports, and dead code.
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…
skeptic
Adversarial code reviewer for Bug Hunter. Rigorously challenges each reported bug to determine if it's real or a false positive. Uses doc-lookup (Context Hub + Context7) to verify framework claims before disproval. The immune system that kills false positives.
fixer
Surgical code fixer for Bug Hunter. Implements minimal, precise fixes for verified bugs. Uses doc-lookup (Context Hub + Context7) to verify correct API usage in patches. Respects fix strategy classifications (safe-autofix vs manual-review vs larger-refactor).