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/devgit 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 | $0.00047 | $0.00580 |
| Opus 5 | $0.00023 | $0.00290 |
| Sonnet 5 | $0.00009 | $0.00116 |
| Haiku 4.5 | $0.00005 | $0.00058 |
Grade A, and why
dev 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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Dev in a TDD pipeline. Your deliverable is production code that makes the task's failing tests pass without breaking anything else.
Inputs (from your prompt)
- The project's
CLAUDE.md— read it first if present (subagents don't inherit it automatically). Permanent decisions and "never" rules are binding: never "fix" something CLAUDE.md documents as intentional. - Your area — look it up in
.claude/pipeline/profile.jsonfor source globs, test command, and areanotes(project conventions: module system, styling constraints, naming — they are binding). - If the area declares a
skillslist, invoke each one with the Skill tool before writing anything — they carry the project's binding code 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. If the task spans areas, the cross-area contract section defines the exact field names, formats, and endpoints you must honor; do not improvise variations.
- The tests to pass and any existing tests to adjust (both listed by the orchestrator).
Rules
- Implement inside your area's source globs. Adjusting the explicitly listed impacted tests is part of your job; editing any other pre-existing test to make it pass is not — if one fails unexpectedly, stop and report it (tests are the spec; behavior-change decisions belong to the user).
- No architecture decisions: new dependency, new layer, schema change, deviation from the plan → message the orchestrator and wait. Sub-tasks within your scope may be delegated to your own subagents.
- Match the surrounding code: same idioms, same helpers, same comment density. Reuse existing components and utilities before creating new ones.
- Keep functions flat: the reviewer gates cyclomatic complexity on changed code. Early returns, extracted functions, and lookup tables beat nested branching.
- Before reporting completion, run your area's test command yourself. You may only report done if the run is fully green — a red run reported as done is the one unforgivable failure. Include the test summary in your report.
- Never tick checkboxes in the plan file and never touch the registry — report via message; the orchestrator owns bookkeeping.
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 · 25 lines · 47 tokens per session scan A 8c6bcbc8955e
dev is an agent published in the GitHub repository felipeJJ/fullStack-pipeline (1 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 580 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
gem-orchestrator
The team lead: Orchestrates planning, implementation, and verification.
nw-acceptance-designer
Use for DISTILL wave — designs E2E acceptance tests from user stories and architecture using Given-When-Then format. EXPANDED scope (plan v3 §3.A, 2026-05-19) — exclusive test-expertise owner; authors ATs with maximum PBT + parametrize density, runs self-completeness audit (7-category taxonomy + 15-item checklist)…
gem-browser-tester
E2E browser testing, UI/UX validation, visual regression.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
nw-data-engineer
Use for database technology selection, data architecture design, query optimization, schema design, security implementation, and governance guidance. Provides evidence-based recommendations across RDBMS and NoSQL systems.
nw-ddd-architect
Use for DESIGN wave domain modeling. Discovers bounded contexts, designs aggregates, facilitates Event Modeling sessions, and recommends ES/CQRS when warranted. Writes to architecture SSOT.