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.
npx skills add jscraik/Agent-Skills --skill he-phase-workgit clone --depth 1 https://github.com/jscraik/Agent-SkillsWrote 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.
[](https://agentmods.dev/skills/jscraik/agent-skills/he-phase-work)<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.
<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00062 | $0.01226 |
| Opus 5.5 | $0.00025 | $0.00490 |
| Sonnet 5.5 | $0.00012 | $0.00245 |
| Haiku 4.5 | $0.00006 | $0.00123 |
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 1mo 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.
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.
- Check live state:
git status --short, branch, plan path, active phase, latest validation, target issue/PR, and blockers. - Verify the plan exists and names the current phase, validation gate, rollback, and stop condition.
- Ensure exactly one matching heartbeat exists or return the heartbeat prompt when automation authority is missing.
- Hand only the active implementation slice to
he-work. - Run the phase validation command after
he-work. If it fails, route tohe-workorhe-code-reviewwith the exact command and output. - Refresh dashboards/browser only after a real validation or eval run.
- 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
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.
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.
- 1mo ago First seen · 110 lines · 62 tokens per session scan A cf4b44f3e947
he-phase-work is a skill published in the GitHub repository jscraik/Agent-Skills (9 stars, last pushed yesterday), licensed Apache-2.0. It adds 62 tokens to every session and 1,226 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
agent-swarm
Agent skill for swarm - invoke with $agent-swarm.
moai-workflow-worktree
Git worktree management for parallel SPEC development with isolated workspaces, automatic branch registration, and seamless MoAI-ADK integration. Use when setting up parallel development environments.
moai-lane-watchdog
One lane stall watchdog iteration: measure lane progress on three channels, classify the stall cause, apply the remedy or resolve the judgment through the decision ladder — instead of waiting on a reply — then record the outcome and report. Reads the unified --auto doctrine at…
moai-workflow-project
Integrated project management system covering documentation, language initialization, template optimization, docs generation, and JIT document loading. Absorbed from moai-workflow-templates, moai-docs-generation, and moai-workflow-jit-docs.
agentrq
Execute tasks assigned by humans or supervisor agents within a specific AgentRQ workspace. Use when you receive channel messages or need to report progress on tasks.
babysit-babysitter-issues
This skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues assigned to a5c-agent in the babysitter repo.