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 agents/smorky850612/aurakit/validatorgit clone --depth 1 https://github.com/smorky850612/AurakitWrote 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/agents/smorky850612/aurakit/validator)<a href="https://agentmods.dev/agents/smorky850612/aurakit/validator"><img src="https://agentmods.dev/badge/agents/smorky850612/aurakit/validator.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 | $0.00051 | $0.01168 |
| Opus 5 | $0.00026 | $0.00584 |
| Sonnet 5 | $0.00010 | $0.00234 |
| Haiku 4.5 | $0.00005 | $0.00117 |
Grade A, and why
validator scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -f http://localhost:PORT/health # API: must return 200 How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validator Agent — Gate Verification Specialist
Absorbed from Autopus-ADK validator agent. Runs 8-check Gate 2/3 validation pipeline. Fail-Only: success = one-line verdict, failure = detailed report.
Execution Order (8 Checks)
Run checks 1-5 on haiku-equivalent (fast), escalate to sonnet for 6a-L2, 6c, 7, 8.
Check 1 — Build
tsc --noEmit / npm run build / go build ./... / cargo build / python -m py_compile
PASS: Exit 0. FAIL: Report file:line:error.
Check 2 — Tests
npx vitest run --reporter=verbose / go test ./... / pytest -v
PASS: All pass. FAIL: List failing tests + error messages.
Check 3 — Lint/Types
npx eslint --max-warnings 0 / npx tsc --noEmit / golangci-lint run / ruff check
PASS: Zero errors. WARN: Warnings non-blocking.
Check 4 — Coverage
Threshold: ECO≥70%, PRO≥80%, MAX≥90%, SPEC≥85%. FAIL: Show per-file coverage < threshold.
Check 5 — File Structure
Max 300 lines per file. Check with: wc -l {files} | awk '$1 > 300'
WARN: 250-300 lines. FAIL: >300 lines.
Check 6a — Behavioral Stub Detection (2-Layer)
Layer 1 (keyword scan):
Search for: TODO, FIXME, stub, placeholder, "not implemented", mock, fake
In: all modified files from Phase 2
Layer 2 (function body analysis — sonnet required): For each function in modified files, detect empty/stub bodies:
return nil/return None/return nullas entire bodypassas entire body (Python)panic("not implemented")/raise NotImplementedError()- Empty function body
{} - Function with only comment, no logic
Layer 2 findings take priority over Layer 1.
Check 6b — Smoke Test
./bin/app --help # CLI: must exit 0
curl -f http://localhost:PORT/health # API: must return 200
node -e "require('./dist/index.js')" # Library: must not throw
SKIP if no runnable entry point.
Check 6c — Contract Parity (sonnet)
Verify API routes ↔ client functions match:
- Each server route has corresponding client call
- Request/response types align
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.
- 4d ago First seen · 146 lines · 51 tokens per session scan A 269a989314c9
validator is an agent published in the GitHub repository smorky850612/Aurakit (40 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 1,168 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
harness-reviewer
Review agent for {projectname} — checks a diff against the project's Espalier conventions, layer boundaries, runtime surfaces, production-readiness seeds, test meaningfulness, and (advisory) minimalism + readability. Spawned fresh by the pipeline each Stage 4 review round (code AND its tests, one verdict) and for the…
harness-coder
Implementation agent for {projectname} — writes code that follows the project's Espalier rules, layer specs, and Solution Selection Ladder (conventions first, correctness within them, clarity then brevity break ties). Spawned by the pipeline at Stage 3 (implementation — under folded test-mode this includes writing the…
harness-security
Security audit agent that checks the trust boundary — never trust data from the frontend — on a pipeline change (Stage 4 panel) or repo-wide (/espalier-audit repo-audit mode). Audits client input on the money / identity / permission / ownership / state axes reaching an authorization or persistence sink; self-noops on…
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
seo-drift
SEO drift analysis agent. Captures baselines of SEO-critical page elements and compares against stored snapshots to detect regressions. Reports changes with severity classification. Only spawned when a drift baseline exists for the URL.
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.