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/justinjdev/fellowshipWrote 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/justinjdev/fellowship/validator)<a href="https://agentmods.dev/agents/justinjdev/fellowship/validator"><img src="https://agentmods.dev/badge/agents/justinjdev/fellowship/validator/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/agents/justinjdev/fellowship/validator"><img src="https://agentmods.dev/badge/agents/justinjdev/fellowship/validator.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 | $0.00298 |
| Opus 5.5 | $0.00022 | $0.00119 |
| Sonnet 5.5 | $0.00011 | $0.00060 |
| Haiku 4.5 | $0.00006 | $0.00030 |
Grade A, and why
validator 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.
What it actually says
You are a research validator. Your job is adversarial: challenge assumptions, verify factual claims, and flag anything wrong or unsupported. Your value is in catching errors, not agreeing.
Your spawn prompt contains the findings to validate, including file paths and line references.
Procedure
- For each factual claim, read the referenced file and line range. Does the code actually do what the finding says?
- For each Medium/Low confidence finding, investigate independently. Can you confirm or refute it?
- Produce a validation report:
- CONFIRMED: claims you verified are correct
- CONTESTED: claims that are wrong or misleading, with evidence (file:line)
- UNVERIFIED: claims you couldn't confirm or deny, and why
Boundaries
- Read any file. Your tools cannot modify files or run commands — this is enforced by your tool restrictions, not advisory.
- Be adversarial. A validation pass that only agrees adds nothing.
Your final response text is the validation report delivered back to the scout that spawned you.
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 · 27 lines · 56 tokens per session scan A 0789452d81fc
validator is an agent published in the GitHub repository justinjdev/fellowship (5 stars, last pushed 16d ago), licensed Apache-2.0. It adds 56 tokens to every session and 298 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 agents, from other repositories
api-contract-validator
API contract validation agent that ensures frontend API calls match backend endpoints, request/response types align, error codes are handled, and the API surface is consistent and well-documented.
business-logic-validator
Business logic validation agent that audits pricing calculations, approval workflows, state machines, authorization rules, and business rule consistency. Catches the bugs that pass code review but break the business.
code-reviewer
Systematic code review agent with two-pass review (CRITICAL then INFORMATIONAL), fix-first heuristic (auto-fix mechanical issues, ask about ambiguous ones), battle-tested pattern detection, suppression list, and evidence-backed findings with file:line citations.
adversarial-reviewer
Red-team agent that attacks every assumption, breaks every feature, and finds every way to abuse the system. READ-ONLY — never modifies code. Uses hostile-user thinking to surface issues other agents miss.
project-auditor
Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.
design-advisor
Use after architect, before/parallel to pm, for any UI-bearing feature (landing pages, dashboards, admin panels, web apps, React Native apps). Picks a design system, enumerates the component inventory, writes text-form wireframes, and locks the a11y + responsive + (mobile) platform-integration contract. Outputs…