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 agentmods add commands/wgo-audit/code/uploadgit clone --depth 1 https://github.com/wgo-audit/codeWhat 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 | $0.00020 | $0.00273 |
| Opus 5 | $0.00010 | $0.00137 |
| Sonnet 5 | $0.00004 | $0.00055 |
| Haiku 4.5 | $0.00002 | $0.00027 |
Grade A, and why
upload 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 yesterday.
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.
What it actually says
/upload
Invoke this as wgo:upload [YYYYMMDD] in Codex,
/wgo:upload [YYYYMMDD] in Claude, or /wgo-upload [YYYYMMDD] in OpenCode.
The date is optional; when omitted, use the newest dated audit root.
Load and use the WGO skill, then run its complete
references/common/upload.md workflow. Upload is an explicit public
publication request, but the workflow still previews and confirms the exact
repository, destination, commit label, and draft PR before external writes.
Automatically repair only the Markdown trailing-whitespace and end-of-file
blank-line defects defined by the workflow. Never otherwise modify the audit to
make it publishable, create or revise its manifest, call a report-repository
generation script, publish a broader-than-public-only evidence boundary
without the auditor's explicit acknowledgement, or overwrite an existing
report. Exclude only disclosed .DS_Store packaging metadata and reject
provider session identifiers anywhere in the public package.
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.
- yesterday First seen · 28 lines · 20 tokens per session scan A eceb507af636
upload is a command published in the GitHub repository wgo-audit/code (2 stars, last pushed 9d ago), licensed MIT. It adds 20 tokens to every session and 273 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 2026-08-31.
Other commands, from other repositories
krait
Run a complete multi-phase security audit on the target codebase.
krait-poc
Write and run a valid Foundry proof-of-concept that proves (or disproves) a Solidity exploit by asserting the actual harm on a forked chain or against local source.
init-brief
Initialize a briefloop workspace using conversational onboarding.
layout
Audit pipeline: choose how the manifest is stored — sharded (an index plus one file per phase: fewer tokens per phase run, parallel-safe across worktrees) or single-file (one file, one diff, no index). A layout CHOICE, not a version upgrade: both shapes are current, neither goes out of date, and this command moves in…
usage
Audit pipeline: token spend attributed by phase, task, model, author and time — with cache economics, cost-per-task and a usage trend. Read-only (never mutates the manifest).
krait-review
Re-examine findings killed by the Critic's automatic gates. Catches over-filtering without compromising the main report's zero-FP standard.