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 SyloRei/claude-godmode --skill profilegit clone --depth 1 https://github.com/SyloRei/claude-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/sylorei/claude-godmode/profile)<a href="https://agentmods.dev/skills/sylorei/claude-godmode/profile"><img src="https://agentmods.dev/badge/skills/sylorei/claude-godmode/profile/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/sylorei/claude-godmode/profile"><img src="https://agentmods.dev/badge/skills/sylorei/claude-godmode/profile.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 | $0.00059 | $0.01357 |
| Opus 5 | $0.00030 | $0.00678 |
| Sonnet 5 | $0.00012 | $0.00271 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
profile 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Profiling
Diagnose a performance problem — high latency, low throughput, excessive memory or allocation — and find the change with the highest payoff for the lowest risk. Measure BEFORE touching code. This skill profiles and recommends; it does not write the optimization.
Auto Mode
Auto Mode suppresses confirmation prompts and proceed-pauses — not the one
clarifying question that can matter here: when the slow path, target metric, or
baseline is unknown, resolve it before profiling (optimizing the wrong path
wastes the whole effort). Ask it the way the shared recommendation convention
(godmode:recommend-convention) in rules/godmode-recommend.md prescribes —
lead with your best-inferred answer for the user to override, not a blank
prompt: e.g. "I'll treat the hot path as the /search endpoint and baseline on
p99 latency — correct me if you meant a different path or metric." "Slow" is not
a target; "p99 request latency is 800ms, want <200ms" is. Once the symptom and
metric are anchored, proceed: baseline, profile, and route the fix without
pausing. Treat course-corrections as normal input.
The Job
- Measure first — establish a baseline and the symptom
- Profile to find the real bottleneck via
@perf-engineer - Route the confirmed optimization
Do NOT skip to the optimization. Find the dominant cost first.
Step 1: BASELINE
- What is the symptom? (slow endpoint, high memory, low throughput)
- What is the target metric and its current value? (latency, throughput, memory)
- How is it measured? (existing benchmark, profiler, timing harness, load test)
Never optimize on intuition. If there is no way to measure the symptom, the first task is to establish one.
Output: "Symptom [X]. Baseline [metric = value]. Target [value]. Measured by [Y]."
Step 2: PROFILE (spawn @perf-engineer)
Spawn @perf-engineer (read-only) to profile against the baseline, locate the
actual hotspot rather than the suspected one, and recommend the highest-payoff,
lowest-risk optimizations. It analyzes; it does not change code.
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.
- 8d ago First seen · 134 lines · 59 tokens per session scan A 2decd1ec1b54
profile is a skill published in the GitHub repository SyloRei/claude-godmode (3 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 1,357 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
debugging-protocol
Systematic protocol for diagnosing broken behavior and making recurrence structurally impossible. Schema mismatch causes 80% of bugs. Use when something isn't showing, isn't working, or is still broken after a fix attempt.
incident-response
Use when production is down, an alert fires, or an incident needs triage. Covers severity classification, communication, timeline tracking, and blameless postmortem with 5 whys. Also use after resolution to write the postmortem.
code-hygiene
Review your codebase for drift introduced by isolated AI sessions: dead exports, duplicate logic, and orphaned types.
performance
Use when code is slow, queries are taking too long, or you suspect N+1 queries, O(n squared) loops, missing indexes, or unbounded result sets.
diagnosing-bugs
Diagnosis loop for hard bugs and performance regressions. Builds a red-capable feedback loop and runs it before hypothesising — complements static code review (which finds bugs by reading) by running actual repros. Use when the user says 'diagnose'/'debug this', or reports something broken/throwing/failing/slow.
issue-debugging
Systematic methodology for issue debugging including root cause analysis, impact mapping, tiered validation plans, and confidence assessment. Use when analyzing bugs, fixing issues, or validating fixes.