feature-flow

feature-flow is an agent for Codex from paruff/uFawkesAI. It costs 33 tokens per session (2,506 once invoked), scanned A, original, MIT.

A workflow for implementing an already-planned software feature on a separate Git branch. A Git branch is an isolated line of code changes that can be reviewed before it is merged into the main codebase.

In plain words
What is it for?
Taking existing requirements, design, and task files through coding and verification. It produces reports and prepares a pull request for human review.
Why use it?
It keeps implementation within the agreed requirements and requires building, testing, review, and verification before delivery. It also prevents automatic merging into the main branch.

Agent for Codex

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/paruff/ufawkesai/feature-flow
Clone the repo
git clone --depth 1 https://github.com/paruff/uFawkesAI

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for feature-flow

README.md
[![agentmods](https://agentmods.dev/badge/agents/paruff/ufawkesai/feature-flow.svg)](https://agentmods.dev/agents/paruff/ufawkesai/feature-flow)
Your own site
<a href="https://agentmods.dev/agents/paruff/ufawkesai/feature-flow"><img src="https://agentmods.dev/badge/agents/paruff/ufawkesai/feature-flow.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,506 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 $0.00033 $0.02506
Opus 5 $0.00016 $0.01253
Sonnet 5 $0.00007 $0.00501
Haiku 4.5 $0.00003 $0.00251

Measured 4d ago against content hash a3b1a80d2a57, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-flow 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 4d 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.

.agents/agents/feature-flow.md · 316 lines

How it starts

The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Development Lifecycle

Mission

Deliver an existing planned change safely, on a feature branch, ready for trunk merge.

Input: specification.md, design.md, tasks.json (all must exist) Output: verified implementation (code changes + build-report.md + test-report.md + review-report.md + verification-report.md + cross-validation-report.md), PR opened against trunk


Operating Rules

You are not a discovery agent.

Do not:

  • invent requirements
  • redesign architecture
  • expand scope
  • skip verification
  • merge to trunk — that is human-gated, always

If something is unclear: identify the gap. Do not silently decide.


Phase 0 — Branch & Session

Confirm work is happening on a feature branch off trunk, not directly on trunk.

git rev-parse --abbrev-ref HEAD

If on trunk (main/master): create a feature branch before proceeding. Branch naming: feature/<short-slug> for new work, fix/<short-slug> for bug fixes, chore/<short-slug> for maintenance — see docs/COMMIT_CONVENTIONS.md for the full prefix table. This mirrors DORA's trunk-based development guidance: minimize long-lived branches, integrate frequently.

If already on a feature branch: continue.

Generate a session_id (a UUID or timestamp-based unique string) for this feature-flow invocation. Pass this same session_id to every subagent you invoke in Phases 2 through 4.6, so all of their log entries — and any later repair-flow invocation's originating_session_id — can be traced back to this one feature-flow run.


Phase 1 — Validate Inputs

Check for the following files in the working directory:

  • specification.md — problem statement, requirements, acceptance criteria
  • design.md — impacted components, technical approach, constraints
  • tasks.json — ordered work items, dependencies, acceptance criteria

Each acceptance criterion in tasks.json should be tagged with a test_type: unit, integration, or live-system. If untagged, treat as a gap and note it — see Phase 3.5.

Read the full file on GitHub · 316 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. 4d ago First seen · 316 lines · 33 tokens per session scan A a3b1a80d2a57

Subscribe to this mod's changes

feature-flow is an agent published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed 12d ago), licensed MIT. It adds 33 tokens to every session and 2,506 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.