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 skills add afaraha8403/balakit --skill blinded-evalgit clone --depth 1 https://github.com/afaraha8403/balakitWrote 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/afaraha8403/balakit/blinded-eval)<a href="https://agentmods.dev/skills/afaraha8403/balakit/blinded-eval"><img src="https://agentmods.dev/badge/skills/afaraha8403/balakit/blinded-eval/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/afaraha8403/balakit/blinded-eval"><img src="https://agentmods.dev/badge/skills/afaraha8403/balakit/blinded-eval.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 | $0.00103 | $0.01290 |
| Opus 5 | $0.00051 | $0.00645 |
| Sonnet 5 | $0.00021 | $0.00258 |
| Haiku 4.5 | $0.00010 | $0.00129 |
Grade A, and why
blinded-eval 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.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blinded eval
Leading words: organic prompt, blinding, isolate, artifacts not self-report, inconclusive is not a pass.
The parent owns the experiment. Candidates never learn they are in an evaluation. The judge sees sanitized labels and the rubric, never variant names. Grade from files written and files opened, never from a candidate's claims.
Skip this skill for typos. A behavior-changing skill or rule draft is the trigger.
Non-negotiables
Copy the first items of the matched steps below into the todo list verbatim.
A step you skip stays with skip: <reason>.
- Frame the variant and write the rubric (3–6 criteria). Hold the rubric back from candidates.
- Isolate each candidate in its own working directory. Plant only organic context. Sanitize names — project-shaped, not experiment-shaped.
- Author one organic user prompt. Same prompt to every candidate.
- Spawn N candidates as isolated subagents. Inherit the host model unless the host exposes distinct model families; then split families across candidates. Do not require Cursor arena, cloud workers, or a specific slug menu.
- Spawn one blinded judge. Prefer a different model family when the host exposes one. The judge sees outputs labeled A/B/C plus the rubric.
- Read every candidate artifact yourself. Compare to the judge. Grade chain-following from what they wrote and opened, not self-report.
- Verdict: promote, iterate, or abandon. Inconclusive is not a pass.
Blinding word list and sanitization: references/blinding.md. Judge prompt template: references/judge-prompt.md.
Phase A — Frame
State, to the user only:
- Variant under test (what changed, vs what baseline).
- Success predicate (falsifiable).
- Rubric: 3–6 concrete criteria the judge will score. Example scale: pass / partial / fail per criterion.
Do not put the rubric, the words eval, rubric, candidate, baseline,
or variant in any directory, filename, or prompt a candidate will see.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 142 lines · 103 tokens per session scan A a2ab8deb83f8
blinded-eval is a skill published in the GitHub repository afaraha8403/balakit (1 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 1,290 once invoked, about $0.0005 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 2026-09-11.
Other skills, from other repositories
comet-verify
A workflow for verifying a Comet change after its coding tasks are complete. Comet is a tool that tracks structured software changes through stages.
working-effectively-with-legacy-code
Apply Michael Feathers-inspired legacy-code rules when changing hard-to-test code safely with characterization tests, seams, sprout methods, or wrap methods.
refactoring-guru
Apply Refactoring.Guru-inspired rules when diagnosing code smells, choosing refactoring techniques, and stopping cleanup before uncontrolled redesign.
refactoring
Apply Martin Fowler-inspired refactoring rules when improving existing code structure while preserving observable behavior.
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.