Borrowing it
Nothing to install: this file belongs to smithersai/smithers. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/smithersai/smithers/main/.agents/skills/flows-jj-abi/SKILL.mdgit clone --depth 1 https://github.com/smithersai/smithersWrote 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/smithersai/smithers/flows-jj-abi)<a href="https://agentmods.dev/skills/smithersai/smithers/flows-jj-abi"><img src="https://agentmods.dev/badge/skills/smithersai/smithers/flows-jj-abi/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/smithersai/smithers/flows-jj-abi"><img src="https://agentmods.dev/badge/skills/smithersai/smithers/flows-jj-abi.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 | $0.00026 | $0.00273 |
| Opus 5.5 | $0.00010 | $0.00109 |
| Sonnet 5.5 | $0.00005 | $0.00055 |
| Haiku 4.5 | $0.00003 | $0.00027 |
Grade A, and why
flows-jj-abi 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 3d 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
flows-jj ABI
Read the ABI campaign, WASM build script, and CONTRIBUTING.md on the revision under test before editing this crate or its committed WASM artifact.
Use a fresh artifact directory for each campaign. The native and committed real-WASM tiers must consume the same deterministic malformed-request corpus; review the reports and hashes, not merely exit status. A smaller local run and an uninstrumented run are narrower evidence than the scheduled campaign and parser ASAN tier. Neither is an exhaustive ABI proof.
The committed WASM bytes have a pinned Rust toolchain and canonical Linux host contract. node packages/smithers/flows/jj-wasm/build-wasm.mjs --verify compares without writing; the script refuses unsupported hosts. Build on the canonical host before committing artifact bytes and run the required gate for the files changed. Retain the seed, case/step counts, artifact hashes, host, and tier status with any reproducibility claim.
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.
- 3d ago Changed 6b02ba3ef270
- 26d ago First seen · 13 lines · 26 tokens per session scan A 8e56208ed4a8
flows-jj-abi is a skill published in the GitHub repository smithersai/smithers (439 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 273 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 2026-09-25.
Other skills, from other repositories
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
rust-tdd
Use when implementing Rust features test-first, reproducing Rust bugs with regression tests, characterizing legacy Rust, or applying red-green-refactor with cargo test. Covers boundary and equivalence cases, proptest shrinking, mockall expectations, rstest fixtures, async/concurrent/CLI tests, and coverage…
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
rust-check
Run cargo check on the current Rust project to find compile errors.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.