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/operationalizegit 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 | $0.00024 | $0.00598 |
| Opus 5 | $0.00012 | $0.00299 |
| Sonnet 5 | $0.00005 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
operationalize 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
/operationalize
Invoke this as wgo:operationalize in Codex, /wgo:operationalize in Claude,
or /wgo-operationalize in OpenCode.
Load and use the WGO skill. Resolve the newest dated audit root with its
references/common/audit-root.md.
Run the complete workflow in its
references/common/operationalization.md.
Hard rules:
- Require a completed or completed-with-open-verification synthesis and explicit auditor approval before drafting operator aids.
- Before writing, announce the required four-part packet and ask whether the auditor wants any optional aid:
worker-data-operations,isolated-rebuild,network-exposure,demo,demo-reset, ordelivery. - Draft documentation only. Do not run commands against environments, authenticate to new systems, deploy, restart, rotate, revoke, migrate, restore, reset data, modify billing, or change routing.
- Every procedure starts
Status: draftorStatus: untested; useexecuted-successfullyonly when canonical evidence records a real authorized execution. - Use exact source locators only when source evidence supports them. Mark a command, prerequisite, threshold, account, fixture, expected output, rollback, or owner
UNKNOWNwhen it has not been established. - Use linked evidence and selected audit artifacts directly. The checklist remains the work view and
controls/open-items.mdholds material future work; operator aids are never competing controls. - Search approved documentation for an existing runbook before drafting each aid. Link and complement an applicable runbook; do not copy it or create a parallel runbook library.
- Create an operating-control strategy only when the completed controls need an explicit stabilization and authority model; it is a derived decision aid, not a second backlog or a runbook.
- Create the four-part transition packet at
operator-aids/:replacement-maintainer,recovery,observability, andiam-and-credential-control. Keep them separate, cross-linked, and evidence-bounded. - Do not create a fixed-size 72-hour mission board. Generate the execution-priority taxonomy instead.
- After the packet is complete, emit the operationalization-complete cutoff and
rerun the Codex, Claude, or OpenCode cost workflow selected from the platform
recorded in
audit-brief.md. Updatecontrols/cost-estimate.mdthrough operationalization without modifying the frozen audit-only cost evidence or charging either cost-calculation phase to the audit. Replacemanifest.json'sexecution.costEstimatewith the refreshedaudit-and-operationalizationresult and validate the manifest again.
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 · 39 lines · 24 tokens per session scan A 74e6257f8dcf
operationalize is a command published in the GitHub repository wgo-audit/code (2 stars, last pushed 9d ago), licensed MIT. It adds 24 tokens to every session and 598 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.