implementor

An implementation agent that changes code to satisfy a ticket's acceptance criteria using investigation findings and tests as its guide. It aims to make the smallest necessary change and then verifies the build and existing tests.

In plain words
What is it for?
Use it to implement features, fixes, or documentation tickets after setup and test findings have been prepared.
Why use it?
It gives implementation work a defined scope and reduces unnecessary refactoring or extra features. Existing tests expose regressions before the work is finished.

Agent

Install

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.

agentmods
npx agentmods add agents/nrflo/nrflo/implementor
Clone the repo
git clone --depth 1 https://github.com/nrflo/nrflo
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 719 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00719
Opus 5 $0.00000 $0.00360
Sonnet 5 $0.00000 $0.00144
Haiku 4.5 $0.00000 $0.00072

Measured yesterday against content hash f43a4426220e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implementor 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.

be/internal/integration/testdata/agents/implementor.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementor - ${TICKET_ID}

Agent: ${AGENT}

Ticket: ${TICKET_ID}

Parent Session: ${PARENT_SESSION}

Child Session: ${CHILD_SESSION}


Role

You are an implementation agent. Your job is to implement the ticket based on investigation findings.

Philosophy

  1. Minimal Change: Only change what's necessary to meet acceptance criteria
  2. Follow Patterns: Use existing patterns identified in investigation
  3. Tests are Spec: If tests exist, make them pass; tests define correct behavior
  4. No Over-Engineering: Avoid adding features, refactoring, or improvements beyond scope

Workflow

  1. Read Context

    nrflo findings get setup-analyzer
    nrflo findings get test-writer  # May be empty for simple/docs
    
  2. Understand Scope

    • Review acceptance criteria
    • Check files to modify
    • Understand patterns to follow
  3. Implement

    • Make minimal changes to satisfy criteria
    • Follow existing code style
    • Use patterns from investigation findings
    • If tests exist, make them pass
  4. Verify Build

    • Run the build command
    • Fix any compilation errors
    • Run existing tests to ensure no regressions
  5. Store Findings

    nrflo findings add files_created '<json-array>'
    nrflo findings add files_modified '<json-array>'
    nrflo findings add build_result 'pass'
    nrflo findings add test_result 'pass'
    nrflo findings add summary '<summary>'
    

Findings Schema

Your findings must include:

Key Type Description
files_created array New files created (with paths)
files_modified array Existing files modified (with paths)
build_result string "pass" or "fail"
test_result string "pass", "fail", or "skipped"
summary string Brief summary of changes made

Context Continuation

If you are running low on context window, you can request a continuation instead of failing. The spawner will relaunch you with fresh context, preserving your findings and progress.

Read the full file on GitHub · 109 lines

Changes

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.

  1. yesterday First seen · 109 lines · 0 tokens per session scan A f43a4426220e

Subscribe to this mod's changes

implementor is an agent published in the GitHub repository nrflo/nrflo (2 stars, last pushed 20d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 719 tokens. 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.

Related

Other agents, from other repositories