implement

An automated workflow for taking one or more OpenSpec feature requests through design, coding, review, and archiving. OpenSpec is a structured way to describe and track software changes.

In plain words
What is it for?
Use it to implement ticketed features, a described feature, or selected work areas from a local backlog.
Why use it?
It separates planning, implementation, and checking so larger changes have a defined process and review step.

Skill for Claude CodeCodex

Part of the specrails plugin — 29 skills, 14 agents shipped together

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 skills/fjpulidop/specrails-core/implement
Any agent
npx skills add fjpulidop/specrails-core --skill implement
Clone the repo
git clone --depth 1 https://github.com/fjpulidop/specrails-core

Made for: Claude Code, Codex.

Or install specrails, the plugin that ships this one along with the rest of its 29 skills, 14 agents.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,899 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 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 $0.00032 $0.11899
Opus 5 $0.00016 $0.05949
Sonnet 5 $0.00006 $0.02380
Haiku 4.5 $0.00003 $0.01190

Measured 3d ago against content hash e12b0566f39d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

implement scanned grade D with 2 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 3d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

grep -q "\.claude/" .gitignore 2>/dev/null

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf .claude/.dry-run/<feature-name>/
specrails-plugin/skills/implement/SKILL.md · 1,090 lines

How it starts

The opening of the file, as written. The whole thing — 1,090 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementation Pipeline

Full OpenSpec lifecycle with specialized agents: architect designs, developer implements, reviewer validates and archives. Handles 1 to N features — adapts automatically (sequential for 1, parallel with worktrees for N).

MANDATORY: Always follow this pipeline exactly as written. NEVER skip, shortcut, or "optimize away" any phase — even if the task seems simple enough to do directly. The orchestrator MUST launch the architect, developer, and reviewer agents as specified. Do NOT implement changes yourself in the main conversation; delegate to the agents defined in each phase. No exceptions.

Input: $ARGUMENTS — accepts three modes:

  1. Ticket numbers (recommended): #85, #71, #63 — implement these specific tickets from the local backlog (local-tickets.json). Skips exploration and selection.
  2. Text description (single feature): "add price history chart" — implement a single feature from a description. Skips exploration and selection.
  3. Area names (fallback): Analytics, UI, Testing — explores areas and picks the best items. Only use if no backlog tickets exist.

IMPORTANT: Before running, ensure Read/Write/Bash/Glob/Grep permissions are set to "allow" — background agents cannot request permissions interactively.


Phase -1: Environment Setup (cloud pre-flight)

This phase runs BEFORE anything else. Detect if we're in a cloud/remote environment and ensure all required tools are available.

Detection

Check the environment variable CLAUDE_CODE_ENTRYPOINT. If it contains remote_mobile or remote_web, OR if CLAUDE_CODE_REMOTE is true, we're in a cloud environment.

Checks to run (sequential, fail-fast)

1. Backlog provider availability
[[ -f ".specrails/local-tickets.json" ]] && echo "Local tickets storage: OK" || echo "WARNING: local-tickets.json not found"
  • Set LOCAL_TICKETS_AVAILABLE=true/false based on file existence.
  • Set GH_AVAILABLE=false (backlog is always local).
  • Set BACKLOG_AVAILABLE=true if local-tickets.json exists.

Read the full file on GitHub · 1,090 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. 3d ago First seen · 1,090 lines · 32 tokens per session scan D e12b0566f39d

Subscribe to this mod's changes

implement is a skill published in the GitHub repository fjpulidop/specrails-core (9 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 11,899 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

knowledge-base

Create and maintain a Markdown knowledge base that any AI agent can read, search, and update. Use when the user wants to start a knowledge base, add or update notes, organize docs/notes for an agent or LLM to consume, build an index of notes, or run a cleanup/maintenance pass on an existing MD knowledge base. Triggers…

wonderwhy-er/DesktopCommanderMCP · 112 tokens

code-review

Use when code has been written and needs validation before committing, or when the user asks for a code review or security check.

darrenhinde/OpenAgentsControl · 28 tokens

test-generation

Use when the user asks for tests, mentions TDD, or when new code has been written and needs test coverage.

darrenhinde/OpenAgentsControl · 27 tokens

scientific-schematics

Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways…

xintaofei/codeg · 68 tokens

statistical-power

Sample-size and statistical power calculations for planning studies. Use whenever someone asks "how many subjects/samples/replicates do I need", wants an a priori power analysis, a minimum detectable effect (MDE), a power curve, or needs to justify a sample size for a grant, IRB protocol, or pre-registration. Covers…

xintaofei/codeg · 190 tokens

build-teaql-app

Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…

teaql/teaql-agent-kit · 112 tokens