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 skills/yonatangross/orchestkit/bare-evalnpx skills add yonatangross/orchestkit --skill bare-evalgit clone --depth 1 https://github.com/yonatangross/orchestkitWrote 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/yonatangross/orchestkit/bare-eval)<a href="https://agentmods.dev/skills/yonatangross/orchestkit/bare-eval"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/bare-eval.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 | $0.00069 | $0.02324 |
| Opus 5 | $0.00034 | $0.01162 |
| Sonnet 5 | $0.00014 | $0.00465 |
| Haiku 4.5 | $0.00007 | $0.00232 |
Grade A, and why
bare-eval scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bare Eval — Isolated Evaluation Calls
Run claude -p --bare for fast, clean eval/grading without plugin overhead.
CC 2.1.81 required. The --bare flag skips hooks, LSP, plugin sync, and skill directory walks.
When to Use
- Grading skill outputs against assertions
- Trigger classification (which skill matches a prompt)
- Description optimization iterations
- Any scripted
-pcall that doesn't need plugins
When NOT to Use
- Testing skill routing (needs
--plugin-dir) - Testing agent orchestration (needs full plugin context)
- Interactive sessions
Prerequisites
# --bare requires ANTHROPIC_API_KEY (OAuth/keychain disabled)
export ANTHROPIC_API_KEY="sk-ant-..."
# Verify CC version
claude --version # Must be >= 2.1.81
Quick Reference
| Call Type | Command Pattern |
|---|---|
| Grading | claude -p "$prompt" --bare --max-turns 1 --output-format text |
| Trigger | claude -p "$prompt" --bare --json-schema "$schema" --output-format json |
| Streaming grade | claude -p "$prompt" --bare --max-turns 1 --output-format stream-json |
| Optimize | echo "$prompt" | claude -p --bare --max-turns 1 --output-format text |
| Force-skill | claude -p "$prompt" --bare --print --append-system-prompt "$content" |
| @-file in prompt | claude -p "grade @fixtures/case-1.md against rubric" --bare (CC 2.1.113 Remote Control autocomplete) |
Long harness runs (CC 2.1.199+): set
CLAUDE_CODE_RETRY_WATCHDOG=1for unattended eval batches — it raises the default retry count for non-capacity transient errors to 300 and lifts the cap of 15 onCLAUDE_CODE_MAX_RETRIES, so an overnight grading run survives transient API blips instead of dying mid-batch.
--output-format stream-json
Newline-delimited JSON events (one per token/tool-call) — lets a runner score partial output or abort early on a failing probe without waiting for the full response.
claude -p "$prompt" --bare --max-turns 1 --output-format stream-json \
| while IFS= read -r line; do
# line is a single JSON event; inspect $.type == "content_block_delta"
jq -r 'select(.type == "content_block_delta") | .delta.text' <<< "$line"
done
What ships with it
9 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.
- references/grading-schemas.md 2.2 KB
- references/invocation-patterns.md 4.8 KB
- references/troubleshooting.md 2.0 KB
- rules/_sections.md 629 B
- rules/bare-grading-only.md 1.4 KB
- rules/bare-plugin-conflict.md 1.0 KB
- rules/bare-requires-api-key.md 1.0 KB
- test-cases.json 1.4 KB
- workflows/skill-fitness.js 4.6 KB runs code
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 · 188 lines · 69 tokens per session scan A 6754a23d8820
bare-eval is a skill published in the GitHub repository yonatangross/orchestkit (225 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 2,324 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
github-actions-ci
Structure GitHub Actions workflows — jobs, steps, caching, matrix builds, secrets, and a quality gate that blocks merges.
ci-cd-best-practices
Use this skill when setting up or improving CI/CD pipelines. Covers automation, testing, and deployment best practices.
excel-connector-governance
Governs driving Excel Online (Business) through a Microsoft Copilot Studio agent against SharePoint-hosted .xlsx. Triggers — "Copilot Studio", "Excel Online (Business)", "add a row", "update a row", "delete a row", "connector 502 / BadGateway", "Office Script", "pin the File input", "spreadsheet agent", "SharePoint…
writing-quality
Audit and rewrite content to remove AI writing patterns ("AI-isms") from deliverables, emails, and any written output. Use this skill whenever generating deliverable content (Phase 1 curation in any client deliverable skill), drafting client emails longer than 3 sentences, writing proposals or SOWs, creating reports…
why-diagnostic
A framing diagnostic for "why did this happen?" moments during agent and tool work. Use when the user says "why did this fail", "why did the agent do that", "why is this output wrong", "why isn't this working", or otherwise asks for an explanation of agent/tool behavior. Reads like an incident report — frame the…
insight-crystallizer
Capture valuable insights, analyses, and decisions from a chat session and file them as persistent markdown so they survive past the current context. Use when a conversation produces something worth keeping — a comparison, a decision with rationale, a research synthesis, a non-obvious debugging finding, a framework.…