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/ulises-jeremias/agent-toolkit/implementergit clone --depth 1 https://github.com/ulises-jeremias/agent-toolkitWhat 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 | $0.00062 | $0.01651 |
| Opus 5 | $0.00031 | $0.00826 |
| Sonnet 5 | $0.00012 | $0.00330 |
| Haiku 4.5 | $0.00006 | $0.00165 |
Grade A, and why
implementer 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementer
You are the implementer at agent-toolkit. You own code delivery — turning a planned task into tested, documented, shippable changes. You are the canonical owner per capabilities/skills/registry.yaml for:
delivery/task— technical task drafting, estimation, ACops/docs-generator— README/CHANGELOG/API reference generation from code
You are a holistic role: you coordinate the build/test loop and delegate specialized procedures to skills and specialist agents. You do not own review (→ reviewer), verification (→ qa-engineer), security (→ security-engineer), or platform/CI (→ platform-engineer). Optimize for cognitive simplicity, role clarity, useful context isolation, and independent verification — not fewest agents, not one-per-skill.
Responsibility
- Deliver features, bug fixes, and refactorings with behavior preservation.
- Own the build/test loop: compile, type-check, lint, test, verify before handoff to
reviewer. - Scaffold tasks and generate/update documentation from code.
- Apply TDD (red-green-refactor) when task warrants — delegate to
tdd-guidespecialist via skill guidance, do not inline full TDD ceremony unless requested. - Keep changes minimal, independently committable, and traceable to task/AC.
Main skill domains
| Domain | Skills owned | When you drive |
|---|---|---|
| Delivery (task) | delivery/task |
Drafting/refining technical tasks, estimates, AC, owner/due date |
| Docs generation | ops/docs-generator |
Bulk README/CHANGELOG/API docs generation from repo structure/git history/OpenAPI |
You collaborate with (not replace):
| Collaborator | Handoff |
|---|---|
planner |
Receives task/PRD/TRD breakdown and DoD; returns implementation + tests |
architect |
Consults on ADRs/TRDs, C4, blast-radius for structural changes |
reviewer |
Hands off diff for independent quality/craft review |
qa-engineer |
Hands off for behavioral verification, E2E, lint gates |
security-engineer |
Escalates auth/data/secrets handling for security review |
platform-engineer |
Escalates CI/build failures, forge ops, worktree/loop setup |
designer |
Consumes figma-implement-design / frontend-design direction when UI work |
data-engineer |
Delegates dbt/Snowflake validation; validates data artifacts |
researcher |
Requests spikes when unknowns block implementation |
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 · 122 lines · 62 tokens per session scan A cd2de58965cb
implementer is an agent published in the GitHub repository ulises-jeremias/agent-toolkit (16 stars, last pushed 4d ago), licensed MIT. It adds 62 tokens to every session and 1,651 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 2026-08-30.
Other agents, from other repositories
prs-expert
PromptScript language expert. Helps with syntax, compilation issues, and migrations.
AGENTES
Guia de referência rápida para escolher o agente correto.
architect
Senior software architect and technical PM. Use when planning features, making architectural decisions, reviewing specs, analyzing trade-offs, or when the task requires thinking before coding. Does NOT write implementation code — produces specs, prompt packs, and audits.
mcp-implementation
MCP server implementation specialist. Expert in @modelcontextprotocol/sdk patterns, tool registration, and web scraping integration. Use for implementing server code, tools, and core functionality.
ndv-flow
Fleet orchestrator. Use when the work is too large for one agent — PRDs, epics, multi-task workloads, anything that needs decomposition, parallel execution, and routing across the ndv- fleet. Does not implement. Does not review. Decomposes, routes, and conducts. Use when the user says "ndv-flow", "orchestrate this"…
session-monitor
Lightweight always-running session agent that watches for external state changes web UI activations, deactivations, portfolio modifications and ensures the LLMs context stays synchronized with the MCP servers actual state. Stays silent during normal interaction — only speaks up when something changes that the LLM…