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.
git clone --depth 1 https://github.com/paruff/uFawkesAIWrote 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/commands/paruff/ufawkesai/oc-health)<a href="https://agentmods.dev/commands/paruff/ufawkesai/oc-health"><img src="https://agentmods.dev/badge/commands/paruff/ufawkesai/oc-health/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/commands/paruff/ufawkesai/oc-health"><img src="https://agentmods.dev/badge/commands/paruff/ufawkesai/oc-health.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 | $0.00015 | $0.00877 |
| Opus 5.5 | $0.00006 | $0.00351 |
| Sonnet 5.5 | $0.00003 | $0.00175 |
| Haiku 4.5 | $0.00002 | $0.00088 |
Grade A, and why
oc-health 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 12d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- doctor — 89% identical, 5 lines differ
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a configuration diagnostician for OpenCode. Perform a comprehensive
health check on this setup. The canonical config lives in this repo's
opencode/ directory and is installed to ~/.config/opencode/ by
opencode/sync.sh — check the installed files (that is what opencode
boots from). Never print a full API key — first 8 characters only.
1. Check Core Configuration Files
Verify existence and syntax of (then run bash opencode/validate.sh ~/.config/opencode
for the determinism invariants):
~/.config/opencode/opencode.jsonc(JSONC — validate by runningopencode debug configand checking it exits 0)~/.config/opencode/fallback.json(pure JSON —python3 -m json.tool <file>)
For each file, report: exists (yes/no), valid syntax (yes/no).
2. Verify Provider Authentication
This setup runs on free channels only: Google models come from
opencode-antigravity-auth's OAuth (Gemini CLI + Antigravity quotas), and the
opencode provider hosts free models — no paid API keys required.
Use !echo $VARIABLE | head -c 8 (first chars only, never the full key):
GEMINI_API_KEY— optional; OAuth is the primary path. Unset is fine (⚠ info).NVIDIA_API_KEY— leftover export in~/.zshrc; nvidia-proxy is REMOVED, so this key is unused → warn if set.OPENROUTER_API_KEY— openrouter fallback hops were removed → info only.OPENCODE_ZEN_TOKEN— unset is fine if auth is stored viaopencode auth.
Also confirm opencode-antigravity-auth is registered (step 4) — without it
the google/* models have no quota source.
3. Validate Agent Model Availability
List the default model and each agent.<name>.model in the installed
opencode.jsonc (there is no tier routing — one explicit model per agent).
For each ID:
- verify it is declared in the installed
opencode.jsoncunderprovider.<name>.models(model definitions must live there — the auth plugin has no config hook; an undeclared model is a validation failure → ✗) - live quota is not testable without spending requests — list the ID for manual verification if you cannot confirm it locally
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.
- 12d ago Changed · +4 tokens per session e2b09ba3d3db
- 14d ago Changed 4d0236a4b6a7
- 15d ago First seen · 80 lines · 11 tokens per session scan A 6af6020f36fc
oc-health is a command published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 877 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 2026-09-27.
Other commands, from other repositories
macos-activity-cleaner
Audit macOS activity and plan capability-preserving cleanup.
bug-report
Structured bug-fix protocol per docs/methodology/bug-protocol.md. Use when asked to '/bug-report', 'I found a bug', 'something is broken', 'fix this bug', 'report a bug', 'this is broken'.
refresh
Refresh only what changed since the last run — incremental re-analysis of the touched components + issue lifecycle, on demand.
audit-self
Run acd against this repository and explain the findings.
harness-doctor
Run AI Harness Doctor full pipeline.
improve-lint
Run the AI-augmented lint self-improvement loop on the current project. Scans .lint-history/ for recurring violation patterns (≥3 hits in 30d window), drafts a Claude-ready prompt to author a new semgrep rule for the top candidate, and surfaces the proposal under .lint-history/proposals/ .md. Non-blocking analysis.…