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 agents/pumblus/okf-harness/verifygit clone --depth 1 https://github.com/pumblus/okf-harnessWrote 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/agents/pumblus/okf-harness/verify)<a href="https://agentmods.dev/agents/pumblus/okf-harness/verify"><img src="https://agentmods.dev/badge/agents/pumblus/okf-harness/verify.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00255 |
| Opus 5 | $0.00000 | $0.00128 |
| Sonnet 5 | $0.00000 | $0.00051 |
| Haiku 4.5 | $0.00000 | $0.00026 |
Grade A, and why
verify 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 5d 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.
What it actually says
Verify loop
The completion bar for every change, run in order:
pnpm -w run test— add or update a test that proves the change.pnpm -w run typecheck— clean.pnpm -w run lint— clean (Biome plus the llms docs freshness check); it must pass before a PR.- CLI behavior changes:
pnpm -w run build, then exercise the built binary, e.g.node packages/cli/dist/main.js check --workspace <ws> --json. Workspace or wiki changes get the sameokfh checktreatment against that workspace.
Use the smallest verifier that proves the change while the work is in progress; the full loop above is the bar before you call a change done.
Every script lives at the workspace root, so keep the -w flag: from a package directory the pnpm <script> shorthand falls back to pnpm exec and reports Command "lint" not found.
Completion: the change is proven by a passing test, pnpm -w run typecheck and pnpm -w run lint are clean, and any CLI change is demonstrated against the built binary.
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.
- 5d ago First seen · 15 lines · 0 tokens per session scan A 5946feaf029c
verify is an agent published in the GitHub repository pumblus/okf-harness (34 stars, last pushed 21d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 255 tokens. 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 2026-08-30.
Other agents, from other repositories
eval-skew-reviewer
Reviews diffs that add or change a write-time enrichment feature / retrieval channel for training-serving skew — verifies the feature is wired into the ONE canonical ingest path AND the eval seed AND the seed liveness contract, so it can't ship "merged-but-inert". Use after changes touching ingest enrichment, a new…
rust-async-safety-reviewer
Reviews Rust async code for tokio + libsql + axum concurrency hazards. Use after changes touching tokio::spawn, axum handlers, libsql connection usage, or any Send/Sync boundaries. Read-only — produces findings, does not edit.
doc-drift-auditor
Read-only audit for fuzzy drift the CI teeth (driftguard.rs) cannot catch — eval numbers stale vs the current env-hash, design-doc/decision rot, memory->repo dangling pointers, and stale worktrees. Run locally on a schedule. Produces a findings report only; never edits.
architect
You are the Architect. Your job is to design the plan before anyone writes code or moves files.
discoverer
You are the Discoverer. Your job is to find and inventory the source material — files, data, configs, code — that will feed downstream agents (Packager, Migrator, etc.).
packager
You are the Packager. Your job is to take a plan (from the Architect) and a manifest (from the Discoverer) and produce the concrete artifact — a directory, a zip, a deploy bundle.