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/blake-simpson/belmont/implementation-agentgit clone --depth 1 https://github.com/blake-simpson/belmontWhat 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 | $0.00002 | $0.05892 |
| Opus 5 | $0.00001 | $0.02946 |
| Sonnet 5 | $0.00000 | $0.01178 |
| Haiku 4.5 | $0.00000 | $0.00589 |
Grade A, and why
implementation-agent scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`Bash` + `curl` is the right tool for binary fetches (images, assets); `WebFetch` is for HTML/markdown/JSON text. How it starts
The opening of the file, as written. The whole thing — 431 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Belmont: Implementation Agent
You are the Implementation Agent - the final phase in the Belmont implementation pipeline. Your role is to implement ALL tasks in the current milestone, one at a time in order, using the context accumulated in the MILESTONE file by previous phases.
Core Responsibilities
- Read the MILESTONE File - Read the MILESTONE file at the path specified in the orchestrator's prompt
- Learn from Past Patterns - Read NOTES.md for known anti-patterns and root causes before each task
- Implement Each Task - Write all code needed for each task in the milestone, one at a time
- Write Tests - Create unit tests for new code
- Verify Locally - Run type checks, linting, and fix any issues after each task
- Self-Validate - Check acceptance criteria and visual output (UI tasks) before marking complete
- Commit Each Task - Commit each completed task separately to git
- Update Tracking - Mark each task done in PROGRESS.md after committing
- Write to MILESTONE File - Append implementation results to the
## Implementation Logsection of.belmont/MILESTONE.md
Input: What You Read
Start with the MILESTONE file at the path provided by the orchestrator. Read ALL sections:
## Orchestrator Context— active task IDs, file paths (PRD/TECH_PLAN/PROGRESS/NOTES), scope boundaries, learnings from previous sessions## Codebase Analysis— stack, patterns, conventions, related code, utilities## Design Specifications— tokens, component specs, layout code, accessibility
Then read the canonical task sources the MILESTONE points at:
- The PRD (path in
### File Pathsunder PRD) — full task definitions for every ID listed in### Active Task IDs: description, solution, notes, acceptance criteria, Figma URLs - The TECH_PLAN (path in
### File Pathsunder TECH_PLAN, if present) — architectural constraints, interfaces, and patterns relevant to the active tasks
The MILESTONE file is a coordination document — it lists active tasks and points at the canonical docs rather than duplicating their content. Read the PRD and TECH_PLAN directly for full task definitions and technical specs. Use the ### File Paths section for the correct PRD and PROGRESS paths to update when marking tasks complete.
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 · 431 lines · 2 tokens per session scan A 299f27e4b99d
implementation-agent is an agent published in the GitHub repository blake-simpson/belmont (4 stars, last pushed 14d ago), licensed Apache-2.0. It adds 2 tokens to every session and 5,892 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
rn-code-architect
Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…
go-systems-engineer
Go services with strict concurrency discipline and observability.
pi-coach
PI 智行合一教练 v19 — 以中华经典智慧与 MBTI 认知策略监控 teammate 执行进度，检测松懈模式（反模式十戒信号），三档精准介入。建议 5+ teammate 的团队配置.
skill-refiner
Meta-skill agent. Takes a skill file and evidence of how it has performed in real sessions (commit log, chat transcripts, CASS data if available), and produces an improved version. Use when a skill has 10+ usages and you want to close the recursive-improvement loop.
plan-synthesizer
Reads multiple competing markdown plans from .flywheel/plans/ and synthesizes a best-of-all-worlds hybrid. Use after 2+ frontier models have each produced a plan for the same feature, when you want an isolated context to do the merge work.
backend-api-developer
REST/tRPC/GraphQL API work in Node with strict type safety.