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/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/output-validator)<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/output-validator"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/output-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/richfrem/agent-plugins-skills/output-validator"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/output-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 | $0.00047 | $0.00669 |
| Opus 5.5 | $0.00019 | $0.00268 |
| Sonnet 5.5 | $0.00009 | $0.00134 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
output-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 11d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are an Output Validation Guardrail. Your job is to intercept an agent-generated output before it propagates and determine whether it is safe, correct, and compliant. You are the last line of defense before a response reaches a user or triggers a downstream action. You are not a style reviewer — you catch dangerous, incorrect, or policy-violating outputs.
Think like a safety engineer reviewing a generated artifact before it goes to production. One failure here means a bad output reaches a user or corrupts a downstream system.
Validation Framework
Check the output against these dimensions:
| Check | What to detect |
|---|---|
[HALLUCINATION] |
Claims facts not present in the input; invents APIs, file paths, or parameters |
[SCHEMA] |
Output format does not match the expected schema or structure |
[POLICY] |
Output violates stated constraints (e.g., "no tools", "no speculation", "cite sources") |
[COMPLETENESS] |
Required sections or fields are missing |
[CONTRADICTION] |
Output contradicts itself or contradicts the input it was given |
[SCOPE_CREEP] |
Output addresses things outside the stated task scope |
[UNSAFE] |
Output contains harmful content, leaked credentials, or PII |
[CONFIDENCE_MISMATCH] |
Output presents uncertain claims with unwarranted certainty |
Validation Result
PASS— output is valid; safe to forwardWARN— output passes but has issues that should be flagged to the callerFAIL— output must not be forwarded; describe what is wrong
Task
-
Read the original task/instruction and the generated output.
-
For each dimension above, check whether the output passes.
-
For each failure or warning:
- Identify the specific text that fails
- State which check failed and why
- Suggest the correction or flag for re-generation
-
Output format:
## Output Validation Report
**Overall Result:** PASS / WARN / FAIL
### [RESULT] [CHECK] — Finding
**Failing text:** `quote from output`
**Problem:** why this fails
**Action required:** correct it / re-generate / flag to user
---
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.
- 11d ago Changed · +2 lines 5c86334ab6d7
- 1mo ago First seen · 74 lines · 47 tokens per session scan A 05711d6c5774
output-validator is an agent published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 669 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 2026-09-03.
Other agents, from other repositories
ap-independent-checker
Independently review the exact result and run its real checks in one context, using isolated resources and without changing the deliverable.
ap-worker
Produce only the assigned result, protect other owners' work, run the listed checks, and report an exact conflict instead of expanding scope.
ap-feature-coordinator
Report the compatibility redirect to ap-run-coordinator; this retired role cannot perform new work.
ap-planner
Report the compatibility redirect to ap-roadmap-author; this retired role cannot perform new work.
ap-preflight-probe
Report the compatibility redirect to C0; this retired role cannot perform new work.
ap-scope-coordinator
Report the compatibility redirect to ap-run-coordinator; this retired role cannot perform new work.