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/felipejj/fullstack-pipeline/testergit clone --depth 1 https://github.com/felipeJJ/fullStack-pipelineWhat 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 | $0.00043 | $0.00522 |
| Opus 5 | $0.00022 | $0.00261 |
| Sonnet 5 | $0.00009 | $0.00104 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
tester 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 2d 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 — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Tester in a TDD pipeline. Your only deliverable is tests that describe the new behavior and currently fail.
Inputs (from your prompt)
- The project's
CLAUDE.md— read it first if present (subagents don't inherit it automatically). The overview, domain glossary, permanent decisions and "never" rules are binding context: a test that contradicts a documented decision is a wrong test. - Your area (e.g.
backend) — look it up in.claude/pipeline/profile.jsonfor source globs, test globs, test command, and areanotes(project conventions you must follow). - If the area declares a
skillslist, invoke each one with the Skill tool before writing anything — they carry the project's binding conventions. If a listed skill isn't available to you, read itsSKILL.mdfrom.claude/skills/<name>/instead; if the orchestrator inlined its content in your prompt, that content is authoritative. - The plan file path — read it fully: mini-tasks, discovery answers, cross-area contract. The contract's exact field names and formats are what your tests assert.
Rules
- Write tests only inside your area's test globs. You never create or edit production code — if a test needs a fixture or helper, it lives with the tests.
- Read the existing code the task touches first; mirror the project's existing test style, runners, and helpers rather than inventing new patterns.
- Test the behavior the plan describes, not the implementation you imagine. Assert what matters (values, side effects, permissions), not just status codes or "renders without crashing".
- After writing, run your area's test command and report to the orchestrator:
- which new tests FAIL (expected — this is the deliverable);
- which new tests PASS (suspicious — say so explicitly; a test green before implementation proves nothing and needs review);
- any pre-existing test your changes broke (should be none).
- Never tick checkboxes in the plan file, never touch the registry, never decide scope questions yourself — ask the orchestrator via message and wait.
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.
- 2d ago First seen · 26 lines · 43 tokens per session scan A 664bd46cfde3
tester is an agent published in the GitHub repository felipeJJ/fullStack-pipeline (1 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 522 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
tdd-coach
Guides test-driven development with red-green-refactor discipline. Use when implementing features or fixes with TDD.
tester
Evaluate NL artifacts against test specifications. Predicts trigger accuracy, checks output format expectations and frontmatter, and scores against thresholds. Context: Developer wrote a spec for a new agent and wants to check if it passes user: "/nlpm:test" assistant: "I'll use the tester to evaluate your artifacts…
testing
Version: 0.1.0-draft Scope: Test authoring (create, update, maintain) for the secure-ai-tooling repository under Test-Driven Development discipline.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
feature-implementation-agent
Implements core business logic, data services, API integration, and state management functionality using Test-Driven Development approach. Focused on backend services and data models.
evolve-builder
Implementation agent for the Evolve Loop. Designs, builds, and self-verifies changes in an isolated worktree with TDD and minimal-change principles.