implement

A set of instructions for implementing changes to BASE's code, specifications, agents, and tools.

In plain words
What is it for?
Planning a verifiable change, updating the relevant spec, writing focused tests, removing replaced code, and running the required checks.
Why use it?
It keeps the requested behavior, its written specification, and the tests aligned while limiting work to what is needed.

Skill for Claude CodeCodex

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/ai-swiss/base/implement
Any agent
npx skills add ai-swiss/base --skill implement
Clone the repo
git clone --depth 1 https://github.com/ai-swiss/base

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 683 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 $0.00034 $0.00683
Opus 5 $0.00017 $0.00342
Sonnet 5 $0.00007 $0.00137
Haiku 4.5 $0.00003 $0.00068

Measured 2d ago against content hash e033fe21b92d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement 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.

.ai/agents/base-contributor/skills/processes/implement/SKILL.md · 57 lines

What it actually says

Implement a change

Build to the highest bar: load skills/competences/code-craft/SKILL.md and apply it to every line. The truth plane and the change plane move together.

Steps

  1. Define done first. The test that proves the behaviour, the command that must go green. Without a verifiable criterion you are not coding; you are hoping.
  2. Work the smallest correct scope. Nothing beyond the change: no speculative config, no error handling for impossible cases, no field "for later".
  3. Code and spec in the same change. When behaviour changes, the specs/current/ leaf changes too (use templates/spec-leaf.md for a new chapter), or the work declares [SPEC-NEUTRAL: reason]. New IDs come from node tools/spec/new-id.mjs; cite them in prose, never restate their proof.
  4. Tests are the specification. Each validated requirement = one named test that would fail without it. Test behaviour, not implementation. Run the narrowest test that can falsify the change; the full suite belongs to verify.
  5. No cohabitation. Whatever the change replaces dies in the same change. Clean up your own orphans (imports, dead code, obsolete tests) in the same diff.
  6. Update the visible record. A public-surface or visible-docs change adds its [Unreleased] line to CHANGELOG.md, or declares [CHANGELOG-SKIP: reason].
  7. Run the adversarial pass on your own diff (the grid in code-craft), then hand off to verify.

What you never do

  • Swallow an error, add a silent fallback, or cap without announcing it.
  • Leave a [A COMPLETER] placeholder or a reference to the plan in committed code.
  • End on red: the change is not done until its narrowest tests pass.
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. 2d ago First seen · 57 lines · 34 tokens per session scan A e033fe21b92d

Subscribe to this mod's changes

implement is a skill published in the GitHub repository ai-swiss/base (42 stars, last pushed 19d ago), licensed Apache-2.0. It adds 34 tokens to every session and 683 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 2026-08-30.

Related

Other skills, from other repositories

a0-contribute-plugin

Guide for publishing an Agent Zero plugin to the community Plugin Index (a0-plugins repo). Covers GitHub repo setup, index.yaml creation, CI validation rules, and PR submission. Use when the user wants to share, publish, submit, or contribute a plugin to the Plugin Hub so other Agent Zero users can find and install it.

agent0ai/agent-zero · 74 tokens

systematic-debug

4-phase root cause analysis and debugging.

modimihir07/agentic-os · 11 tokens

a0-contribute-plugin

Guide for publishing an Agent Zero plugin to the community Plugin Index (a0-plugins repo). Covers GitHub repo setup, index.yaml creation, CI validation rules, and PR submission. Use when the user wants to share, publish, submit, or contribute a plugin to the Plugin Hub so other Agent Zero users can find and install it.

Gen-Verse/PAST-Bench · 74 tokens

Code Review

Review a patch, diff, PR, or implementation for bugs, regressions, risky assumptions, and missing tests.

notforyou23/home23 · 26 tokens

contribution-pipeline

Full issue-to-PR lifecycle with 5-phase gated pipeline. Produces contributions maintainers look forward to — project-aware, thoroughly tested, security-gated, well-documented. Skill bundle with sub-skills for security, test quality, documentation, clean-room verification, and vault integration.

magnus919/hermes-profiles · 63 tokens

hapo:hotfix

ALWAYS activate this skill when you are asked to FIX a bug, error, test failure, CI/CD issue, type error, lint error, log error, UI issue, or code problem. Uses hapo:debug for evidence-first diagnosis before any code change.

haposoft/cafekit · 58 tokens