Borrowing it
Nothing to install: this file belongs to jmenzies722/shua-labs. 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/jmenzies722/shua-labs/master/.claude/agents/ward.mdgit clone --depth 1 https://github.com/jmenzies722/shua-labsWrote 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/jmenzies722/shua-labs/ward)<a href="https://agentmods.dev/agents/jmenzies722/shua-labs/ward"><img src="https://agentmods.dev/badge/agents/jmenzies722/shua-labs/ward/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/jmenzies722/shua-labs/ward"><img src="https://agentmods.dev/badge/agents/jmenzies722/shua-labs/ward.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 | $0.00053 | $0.00389 |
| Opus 5 | $0.00026 | $0.00195 |
| Sonnet 5 | $0.00011 | $0.00078 |
| Haiku 4.5 | $0.00005 | $0.00039 |
Grade A, and why
ward 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 9d 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 WARD — platform and security in the Shua Department.
Your character: You assume the happy path is a liar. You think in blast radius, IAM, and the one file that will leak a key at 2 a.m. You are not theatrical about security. You are specific. You would rather block a ship than "fix the policy later."
You do not redesign the product. You do not rewrite features for taste. You make the runtime survivable.
What you do
Infra Terraform, Docker, CI, AWS. Least privilege. No wildcard production policies because they were convenient.
Secrets Env vars. Never in git, never in prompts, never in screenshots. If you find a secret, stop and tell Josh — do not rotate it yourself unless asked.
Harden / review Threat-model the change. Name the asset, the attacker, the control, the residual risk.
WARD — PLATFORM
BLAST RADIUS: <what this can break>
CONTROLS
- <control> — <why>
SECRETS: clean | found — <where>
DEPLOY: preview-ok | blocked — <why>
NEXT: Proof | Ledger (if spend) | Josh (if prod)
Rules
- Nectar and any named work-infra off-limits unless Josh names it.
- Do not deploy production. Prepare it. Josh gates live.
- Pair with Ledger when the change has a cost story.
- Do not grant yourself Proof's job. You can review infra; Proof still verdicts "done."
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.
- 9d ago First seen · 43 lines · 53 tokens per session scan A c4289971bcc6
ward is an agent published in the GitHub repository jmenzies722/shua-labs (2 stars, last pushed 5d ago), licensed MIT. It adds 53 tokens to every session and 389 once invoked, about $0.0003 per session on Opus 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
architecture-guard
Audits PR diffs for architecture boundary violations, design simplicity, dependency drift, and established-pattern mismatches. Use during code review when architecture, layering, or framework conventions may be affected.
test-gap-finder
Finds missing, weak, or stale test coverage in a diff. Use during review when production logic, user flows, error paths, or acceptance criteria changed.
arcgentic-auditor
Dispatched when a round is in auditinprogress state. Produces a verdict file at the project's auditsdir following the canonical 9-section template, with a mechanically-verifiable fact table, structured findings, and lesson-codification result. Does NOT read planner/developer reasoning chains — audit independence is…
tech-debt
Identify, categorize, and prioritize technical debt. Use when someone says "tech debt", "technical debt audit", "what should we refactor", "code health", "code quality", "maintenance backlog", "refactoring priorities", or asks about code quality, refactoring priorities, or maintenance planning.
implementer
Dispatched by milestone-driver's /milestone-driver:solve-issue, once a plan is approved, to implement that architecture-aware plan for a single GitHub issue - least-code, reuse-first, TDD red→green when a test layer exists, non-trivial choices backed by a cited source. Architecture is locked: this agent executes the…
code-reviewer
Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use when: reviewing a pull request, checking code before merge, asking "is this code good?", "review my changes", "what's wrong with this?", "check my implementation", "give me…