he-phase-work

he-phase-work is a skill for Codex from jscraik/Agent-Skills. It costs 62 tokens per session (1,226 once invoked), scanned A, original, Apache-2.0.

A workflow skill for carrying out an approved development plan one phase at a time, with checks before and after each phase.

In plain words
What is it for?
Use it to continue an approved issue or pull request through controlled implementation phases, run checks, and report blockers or the next safe action.
Why use it?
It helps prevent work from continuing when the plan, permissions, repository state, or validation rules are unclear.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions subagents.

Good fit Use it to continue an approved issue or pull request through controlled implementation phases, run checks, and report blockers or the next safe action.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jscraik/agent-skills/he-phase-work
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.

Any agent
npx skills add jscraik/Agent-Skills --skill he-phase-work
Clone the repo
git clone --depth 1 https://github.com/jscraik/Agent-Skills

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 he-phase-work

README.md
[![agentmods](https://agentmods.dev/badge/skills/jscraik/agent-skills/he-phase-work/github.svg)](https://agentmods.dev/skills/jscraik/agent-skills/he-phase-work)
Your own site
<a href="https://agentmods.dev/skills/jscraik/agent-skills/he-phase-work"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/he-phase-work/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for he-phase-work

Your own site · 80×15
<a href="https://agentmods.dev/skills/jscraik/agent-skills/he-phase-work"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/he-phase-work.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,226 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00062 $0.01226
Opus 5 $0.00031 $0.00613
Sonnet 5 $0.00012 $0.00245
Haiku 4.5 $0.00006 $0.00123

Measured 8d ago against content hash cf4b44f3e947, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

he-phase-work 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 8d 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.

Plugins/harness-engineering/skills/he-phase-work/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HE Phase Work

Philosophy

Move an approved plan one safe phase at a time. The heartbeat wakes the thread; this skill decides whether the next phase is safe and delegates implementation to he-work.

When to Use

Use when the user asks to continue an approved plan, issue, PR, or recurring implementation loop with phase gates, validation, and optional Linear updates.

When Not to Use

Use he-work for one-off implementation. Use he-plan or he-spec when the phase sequence is not approved. Stop if plan path, active phase, edit authority, Linear authority, or validation gate is unclear.

Inputs

Approved plan path, target issue/PR, active phase, branch/dirty state, validation command, heartbeat authority, Linear authority, staging authority, and provenance evidence when cited.

Outputs

Return phase status: active phase, gates, validation outcomes, heartbeat status, Linear update status, git staging status, blockers, and next safe action.

Procedure

Apply the context-disposition policy: move important still-valid context to references, and intentionally discard stale, duplicated, unsafe, superseded, or low-signal text.

  1. Check live state: git status --short, branch, plan path, active phase, latest validation, target issue/PR, and blockers.
  2. Verify the plan exists and names the current phase, validation gate, rollback, and stop condition.
  3. Ensure exactly one matching heartbeat exists or return the heartbeat prompt when automation authority is missing.
  4. Hand only the active implementation slice to he-work.
  5. Run the phase validation command after he-work. If it fails, route to he-work or he-code-review with the exact command and output.
  6. Refresh dashboards/browser only after a real validation or eval run.
  7. Ask before Linear mutation, staging, commit, push, or closure.

Validation

Fail fast: stop at the first failed gate and do not proceed until fixed, waived by an authorized gate, or reported as blocked.

git status --short
git branch --show-current
test -f <approved-plan-path>
rg -n "phase|gate|validation|blocked|rollback" <approved-plan-path>
./bin/ask skills audit <touched-skill-path> --level strict --json --robot

Read the full file on GitHub · 110 lines

Files

What ships with it

5 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. 8d ago First seen · 110 lines · 62 tokens per session scan A cf4b44f3e947

Subscribe to this mod's changes

he-phase-work is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 10d ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,226 once invoked, about $0.0003 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 2026-09-03.