Borrowing it
Nothing to install: this file belongs to vohongtho/code-intel-platform. 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/vohongtho/code-intel-platform/main/.claude/skills/code-intel/eval/SKILL.mdgit clone --depth 1 https://github.com/vohongtho/code-intel-platformWrote 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/vohongtho/code-intel-platform/eval)<a href="https://agentmods.dev/skills/vohongtho/code-intel-platform/eval"><img src="https://agentmods.dev/badge/skills/vohongtho/code-intel-platform/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/vohongtho/code-intel-platform/eval"><img src="https://agentmods.dev/badge/skills/vohongtho/code-intel-platform/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 | $0.00056 | $0.00813 |
| Opus 5.5 | $0.00022 | $0.00325 |
| Sonnet 5.5 | $0.00011 | $0.00163 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
eval
29 symbols | 6 files | path:
eval/| call density: 0.2/sym
When to Use
Load this skill when:
- The task involves code in
eval/ - The user mentions
run,start,callor asks how they work - Adding, modifying, or debugging eval-related functionality
- Tracing call chains that pass through the eval layer
Key Files
| File | Symbols | Notes |
|---|---|---|
eval/run-mcp-bench.mjs |
McpClient, constructor, start, _sendRaw +(5) |
internal |
eval/run-agent-bench.mjs |
runCLI, grepFile, readFile, score +(3) |
internal |
eval/run-eval-langs.mjs |
runCLI, pass, fail, check |
internal |
eval/run-eval.mjs |
pass, fail, run, check |
internal |
eval/run-eval-multi.mjs |
pass, fail, run |
internal |
eval/summarize.mjs |
col, col2 |
internal |
Hot Symbols
Sorted by call graph degree (changing these has the highest blast radius):
| Symbol | Kind | In ← | → Out | File |
|---|---|---|---|---|
run |
function | 19 | 0 | eval/run-eval.mjs |
start |
method | 6 | 7 | eval/run-mcp-bench.mjs |
call |
method | 3 | 5 | eval/run-mcp-bench.mjs |
stop |
method | 6 | 0 | eval/run-mcp-bench.mjs |
bench |
function | 1 | 4 | eval/run-mcp-bench.mjs |
baselineAnswer |
function | 1 | 3 | eval/run-agent-bench.mjs |
readFile |
function | 3 | 0 | eval/run-agent-bench.mjs |
enhancedAnswer |
function | 1 | 2 | eval/run-agent-bench.mjs |
runCLI |
function | 2 | 0 | eval/run-agent-bench.mjs |
pass |
function | 1 | 1 | eval/run-eval-langs.mjs |
fail |
function | 1 | 1 | eval/run-eval-langs.mjs |
pass |
function | 1 | 1 | eval/run-eval.mjs |
Execution Flows
8 execution path(s) pass through this area.
Run code-intel inspect <symbol> on a hot symbol to trace the full call chain.
Impact Guidance
Before modifying any symbol in this area:
- High-degree symbols (In ← ≥ 3) — check all callers before changing signatures
- Entry points — changes propagate to external consumers
- Run
code-intel impact <symbol>to get full blast radius
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.
- 1mo ago First seen · 70 lines · 56 tokens per session scan A f80dff5f60d3
eval is a skill published in the GitHub repository vohongtho/code-intel-platform (3 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 813 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.