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.
git clone --depth 1 https://github.com/JSK9999/ai-nexusWrote 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/commands/jsk9999/ai-nexus/eval)<a href="https://agentmods.dev/commands/jsk9999/ai-nexus/eval"><img src="https://agentmods.dev/badge/commands/jsk9999/ai-nexus/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/commands/jsk9999/ai-nexus/eval"><img src="https://agentmods.dev/badge/commands/jsk9999/ai-nexus/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 | $0.00000 | $0.00609 |
| Opus 5.5 | $0.00000 | $0.00244 |
| Sonnet 5.5 | $0.00000 | $0.00122 |
| Haiku 4.5 | $0.00000 | $0.00061 |
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.
This is a copy
89% identical to eval — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eval Command
Manage eval-driven development workflow.
Usage
/eval [define|check|report|list] [feature-name]
Define Evals
/eval define feature-name
Create a new eval definition:
- Create
.claude/evals/feature-name.mdwith template:
## EVAL: feature-name
Created: $(date)
### Capability Evals
- [ ] [Description of capability 1]
- [ ] [Description of capability 2]
### Regression Evals
- [ ] [Existing behavior 1 still works]
- [ ] [Existing behavior 2 still works]
### Success Criteria
- pass@3 > 90% for capability evals
- pass^3 = 100% for regression evals
- Prompt user to fill in specific criteria
Check Evals
/eval check feature-name
Run evals for a feature:
- Read eval definition from
.claude/evals/feature-name.md - For each capability eval:
- Attempt to verify criterion
- Record PASS/FAIL
- Log attempt in
.claude/evals/feature-name.log
- For each regression eval:
- Run relevant tests
- Compare against baseline
- Record PASS/FAIL
- Report current status:
EVAL CHECK: feature-name
========================
Capability: X/Y passing
Regression: X/Y passing
Status: IN PROGRESS / READY
Report Evals
/eval report feature-name
Generate comprehensive eval report:
EVAL REPORT: feature-name
=========================
Generated: $(date)
CAPABILITY EVALS
----------------
[eval-1]: PASS (pass@1)
[eval-2]: PASS (pass@2) - required retry
[eval-3]: FAIL - see notes
REGRESSION EVALS
----------------
[test-1]: PASS
[test-2]: PASS
[test-3]: PASS
METRICS
-------
Capability pass@1: 67%
Capability pass@3: 100%
Regression pass^3: 100%
NOTES
-----
[Any issues, edge cases, or observations]
RECOMMENDATION
--------------
[SHIP / NEEDS WORK / BLOCKED]
List Evals
/eval list
Show all eval definitions:
EVAL DEFINITIONS
================
feature-auth [3/5 passing] IN PROGRESS
feature-search [5/5 passing] READY
feature-export [0/4 passing] NOT STARTED
Arguments
$ARGUMENTS:
define <name>- Create new eval definitioncheck <name>- Run and check evalsreport <name>- Generate full reportlist- Show all evalsclean- Remove old eval logs (keeps last 10 runs)
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 · 121 lines · 0 tokens per session scan A 7c8e20c65995
eval is a command published in the GitHub repository JSK9999/ai-nexus (19 stars, last pushed 7mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 609 tokens. A static security scan graded it A with 0 findings. It is 89% identical to eval, differing in 4 lines, and is treated as a copy.
Other commands, from other repositories
hatch3r-bug-pipeline
Run a known-cause bug fix through a 3-phase test-first pipeline -- reproduce + root-cause, regression-test + fix together, then root-cause-depth review -- with full sub-agent delegation.
implement
Execute tasks from a track's implementation plan following TDD workflow.
assess
Ground one dependency-update request against this repository as it exists right now, and decide whether an update is actually owed. You produce an assessment and a verdict; you change nothing. No one watches the run; the assessment file and your declared fields are the only things that persist.
review-tests
Find this class of defect: the change establishes or alters meaningful behavior, and no test would fail when that behavior regresses in a plausible way. Tests protect outcomes and invariants — count, lines, and coverage percentages are not outcomes. Not every change needs a test, and a change with none is not a…
discover-checks
Find the project's own checks and declare them. You do not run the gate: a script runs exactly what you declare, for as long as it takes, and records every exit status. Your declaration is the whole of what gets validated, so it must be the project's gate and nothing else.
classify-red
The project's gate ran and at least one check failed. $ARTIFACTSDIR/validation.md is the record: every check that ran, its group, its exit status, each failing check's output tail, and the path of each check's full output log. Decide why the failed checks failed, judging every one the record names. You fix nothing and…