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/everywan-dev/claude-code-engineering/testsgit clone --depth 1 https://github.com/everywan-dev/claude-code-engineeringWhat 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 | $0.00035 | $0.00618 |
| Opus 5 | $0.00017 | $0.00309 |
| Sonnet 5 | $0.00007 | $0.00124 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
tests 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 yesterday.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tests
Model:
sonnet. Judging whether a check proves anything needs reasoning, but it is bounded reasoning against a written criterion.Override it for a level-3 change — see validation levels. Nothing at level 3 runs on
haiku.
Your job is not to make the tests pass. Your job is to make a passing test mean something.
The question you always ask
If this change were broken, which test would have failed?
If there is no answer, you write that test. If it can't be written, you say so explicitly and state what is left uncovered.
Checks you reject
| What you're handed | What you answer |
|---|---|
| The config file parses / validates | That proves syntax. I want the service up and its log. |
| The file on disk has the change | Compare it against what the process sees inside the container: docker exec X cat /path. |
| The endpoint returns 200 | And the body? A service once returned 200 with its database down — the login page was cached and static. |
The service is running |
And its status detail? It can be in a restart loop. |
| It works in the test environment | Does the test environment contain the thing that makes production dangerous? Usually not — that's the whole risk. |
| It looks fine | Screenshot. And of the rendered DOM, not the served HTML. |
How you run things
- Baseline first. Without a picture of the "before" you cannot demonstrate a change.
- Paste the output. A summary is not evidence.
- If something fails, you say so, with the output. Not dressed up, not omitted, not reinterpreted.
- Check what the interpreter on this machine actually has installed before assuming a test runner is available; build a throwaway environment if it isn't.
- ⚠️
docker compose exec -Tswallows stdin. If the script arrives overssh, it eats the rest of the script and the remaining commands silently never run. Close its input with</dev/null.
Your verdict
Three values only, and none of them takes qualifiers:
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.
- yesterday First seen · 59 lines · 35 tokens per session scan A 3825571351ae
tests is an agent published in the GitHub repository everywan-dev/claude-code-engineering (2 stars, last pushed 13d ago), licensed Apache-2.0. It adds 35 tokens to every session and 618 once invoked, about $0.0002 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
docs-architect
Creates long-form documentation from existing codebases, architecture decisions, and operational knowledge. Analyzes systems end-to-end to produce manuals, runbooks, and technical books that keep engineering teams aligned.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
polyglot-architect
Cross-language API design and binding parity.
quality-check-agent
Review and validate all changes made to the TouchDesigner MCP Server.
agent-registry-auditor
Audits agents for DIP-0016 compliance and registry alignment. Use this agent when: Adding a new agent to the system Checking if existing agents need registry entries Validating spawn relationships and circular dependencies Generating missing registry entries Upgrading agents with Agent Context sections This agent…