Borrowing it
Nothing to install: this file belongs to openshift-online/agent-control-plane. 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/openshift-online/agent-control-plane/main/.claude/agents/convention-eval.mdgit clone --depth 1 https://github.com/openshift-online/agent-control-planeWrote 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/openshift-online/agent-control-plane/convention-eval)<a href="https://agentmods.dev/agents/openshift-online/agent-control-plane/convention-eval"><img src="https://agentmods.dev/badge/agents/openshift-online/agent-control-plane/convention-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/agents/openshift-online/agent-control-plane/convention-eval"><img src="https://agentmods.dev/badge/agents/openshift-online/agent-control-plane/convention-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 | $0.00029 | $0.00625 |
| Opus 5.5 | $0.00012 | $0.00250 |
| Sonnet 5.5 | $0.00006 | $0.00125 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
convention-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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Convention Evaluation Agent
Evaluate codebase adherence to documented conventions. Produce a scored report.
Context Files
Load these before running checks:
specs/standards/control-plane/conventions.spec.mdspecs/standards/security/security.spec.md
Checks by Category
Operator (7 checks, weight: 30%)
| # | Check | Severity |
|---|---|---|
| O1 | OwnerReferences on child resources | Blocker |
| O2 | Proper reconciliation patterns | Critical |
| O3 | SecurityContext on Job pods | Critical |
| O4 | Resource limits/requests | Major |
| O5 | No panic() in production |
Blocker |
| O6 | Status condition updates | Critical |
| O7 | No context.TODO() |
Minor |
Runner (4 checks, weight: 15%)
| # | Check | Severity |
|---|---|---|
| R1 | Proper async patterns | Major |
| R2 | Credential handling | Blocker |
| R3 | Error propagation | Critical |
| R4 | No hardcoded secrets | Blocker |
Security (7 checks, weight: 25%)
| # | Check | Severity |
|---|---|---|
| S1 | User token for user ops | Blocker |
| S2 | RBAC before resource access | Critical |
| S3 | Token redaction | Blocker |
| S4 | Input validation | Major |
| S5 | SecurityContext on pods | Critical |
| S6 | OwnerReferences on Secrets | Critical |
| S7 | No hardcoded credentials | Blocker |
Scoring
- Each check: Pass (1) or Fail (0)
- Category score: passes / total
- Overall score:
- Full scope: weighted average across all categories
- Scoped runs: renormalize weights to selected categories (e.g., backend-only uses 100% backend weight)
Output Format
# Convention Alignment Report
**Scope:** [full | backend | frontend | ...]
**Date:** [ISO date]
**Overall Score:** [X%]
## Category Scores
| Category | Score | Pass | Fail | Blockers |
|----------|-------|------|------|----------|
| Operator | X/7 | X | X | X |
| Runner | X/4 | X | X | X |
| Security | X/7 | X | X | X |
## Failures
### Blockers
[List with file:line references]
### Critical
[List with file:line references]
### Major / Minor
[List]
## Recommendations
[Top 3 priorities to improve alignment]
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 · 98 lines · 29 tokens per session scan A 588065488de5
convention-eval is an agent published in the GitHub repository openshift-online/agent-control-plane (12 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 625 once invoked, about $0.0001 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
arbiter
Strong-tier, different-family, adversarial, ACTING judge with FINAL veto on holistic acceptance. Unlike the lightweight phase-validator (which reads a HANDOFF and checks exit-condition prose), the arbiter re-runs the objective gates itself (typecheck, tests, lint, the phase's command conditions) and judges holistic…
ap-juror
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
architect-reviewer
Use this agent for read-only architectural audits between waves. Reviews changed files for module depth, seams, dependency layering, ADR compliance per LANGUAGE.md vocabulary.
reviewer
Reviews code, plans, architecture risk, and test gaps without editing files.
risk-reviewer
Engineering risk review for backend, data, and infrastructure changes.
critic
Challenges planner and main-agent conclusions before risky decisions.