implement

implement is a skill for Claude Code, Codex from mishahanin/heading-os. It costs 64 tokens per session (4,406 once invoked), scanned C, original, Apache-2.0.

An implementation skill that carries out an approved software plan one step at a time. It records the progress and can run a final check that the expected files and changes are present.

In plain words
What is it for?
Use it after creating an implementation plan when the user asks to build or execute it. It handles the plan’s steps in order and can optionally record a machine-readable trajectory for later evaluation.
Why use it?
It provides a repeatable way to execute a prepared plan and spot incomplete work. The progress record also makes the run easier to review afterward.

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/mishahanin/heading-os/implement
Any agent
npx skills add mishahanin/heading-os --skill implement
Clone the repo
git clone --depth 1 https://github.com/mishahanin/heading-os

Made for: Claude Code, 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 implement

README.md
[![agentmods](https://agentmods.dev/badge/skills/mishahanin/heading-os/implement.svg)](https://agentmods.dev/skills/mishahanin/heading-os/implement)
Your own site
<a href="https://agentmods.dev/skills/mishahanin/heading-os/implement"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/implement.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,406 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00064 $0.04406
Opus 5 $0.00032 $0.02203
Sonnet 5 $0.00013 $0.00881
Haiku 4.5 $0.00006 $0.00441

Measured today against content hash 93abf39fd321, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

implement scanned grade C 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 today.

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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

This is a **soft** reminder, not a block. If Misha says proceed (or has already implied it), continue to Phase 0. Never refuse to implement on a MISSING result — CEO sovereignty holds.
.claude/skills/implement/SKILL.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement

Execute an implementation plan created by /create-plan. Read the plan thoroughly, execute each step in order, emit a structured trajectory for every phase boundary, and report on the completed work.

Version history (v1.3-v1.8): the emission discipline changed over several versions. Version 1.6 added typed flags (one Bash call per event, no temp file). Version 1.7 added the emit-time sequencing guard (exit 5) and the run-level --verify files reconciliation. Version 1.8 fixed --verify's blindness to bracketing defects (orphan wave_end reconciliation, out-of-bracket step_end detection, advisory flags for a wave_start missing its declared shape). The Trajectory emission contract below carries the authoritative invariants, restated in Phase 2, Phase 5, and the NEVER list. The full per-version changelog is in references/implement-details.md.

Trajectory emission contract

The trajectory (outputs/operations/implement/_trajectory_<run_id>.jsonl) is the input to /scrutinize trajectory:<run_id> audits (Agent-as-a-Judge, DevAI benchmark) and a verbatim audit record: emit through the helper only, never edit it. All emission is skipped under --no-trajectory. The invariants, enforced by the phases below and self-checked by --verify:

  • Pairing. Every step_start has a matching step_end (same step number); step 0 (plan-load) is paired too. Every wave_start has a wave_end.
  • Sequencing (sequential waves / no-wave runs). Emit each step_end before the next step_start; never open step N+1 while step N is open. The helper enforces this at emit time (v1.7). A step_start opened while another step is still open exits 5 and does not land. A step_end for an unopened step does the same. To clear it, emit the missing marker first, or open a parallel wave_start for legitimate interleaving. If work genuinely reorders, emit a deviation that records the swap (the M1 discipline). Emit a step-scoped deviation as well when a run defers a plan-declared terminal action. The final [0 0] push that a step's success criteria mandate is one such action. The same holds when a run reverses an approved decision mid-run, or diverges from explicit plan text at all. Even a trivial, functionally-identical substitution such as re-sourcing an import counts. A step_end note alone is not enough, because the structured trajectory must match the plan's Deviations section. Parallel-wave member steps may legitimately interleave inside their wave bracket, because an open parallel wave suspends the guard.
  • Wave bracketing. wave_start precedes the wave's first step_start, and wave_end follows all member step_ends. wave_end.successes equals the count of bracketed step_end with status ok or deviation, not the declared membership. Once a run emits any wave event, EVERY step but step 0 belongs to a bracket, and every wave_start carries --step-count and --parallel/--no-parallel. --verify checks all three since v1.8 (an orphan wave_end no longer buys its successes claim a free pass).
  • Literal paths. --file takes one literal path per real file touched: no globs, brace-shorthand, or count strings (the N1 discipline).
  • Whole-wave deferral. A wave not executed at all emits no wave_start/wave_end; instead one wave-scoped deviation keyed to the wave's first step (--scope wave --wave N).

Read the full file on GitHub · 293 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. today Changed 93abf39fd321
  2. 4d ago First seen · 293 lines · 64 tokens per session scan C 2234c87005f6

Subscribe to this mod's changes

implement is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed today), licensed Apache-2.0. It adds 64 tokens to every session and 4,406 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). 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

create-modal

Create declarative modals using the modal library API. Covers modal types (confirm, input, select, form), sections (Text, Buttons, Input, Textarea, Checkbox, List, Combo, When, Custom), rendering with OverlayModal, and keyboard/mouse handling. Use when adding modals or dialogs to the application.

marcus/sidecar · 69 tokens

merge-strategy

Git merge strategies, conflict resolution approaches, merge vs rebase recommendations, and branch integration patterns in sidecar. Covers pull strategy menu, direct merge workflow, squash merge, commit message templates, configurable defaults, and protected branches. Use when working on git merge features or making…

marcus/sidecar · 63 tokens

autoprompt

Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.

Spielewoy/autoprompt-skill · 56 tokens

autoprompt

Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.

Spielewoy/autoprompt-skill · 56 tokens

openlore-brainstorm

Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.

clay-good/OpenLore · 40 tokens

ap-juror

L4 terminal leaf - G7 SIGN-OFF. One independent sign-off panel seat that saw none of the intermediate work. Binary PASS/FAIL on opened evidence; default-FAIL. A FAIL naming a P0/P1 blocker is NOT arbitrable into PASS.

Spielewoy/autoprompt-skill · 58 tokens