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-specgit 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-spec)<a href="https://agentmods.dev/skills/jscraik/agent-skills/he-spec"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/he-spec/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-spec"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/he-spec.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 | $0.00048 | $0.02558 |
| Opus 5.5 | $0.00019 | $0.01023 |
| Sonnet 5.5 | $0.00010 | $0.00512 |
| Haiku 4.5 | $0.00005 | $0.00256 |
Grade A, and why
he-spec 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Engineering Spec
Philosophy
Make approved intent testable without doing the plan's job. Turn one selected HE slice into a bounded behavior contract with source truth, uncertainty, acceptance evidence, validation, rollback, and handoff boundaries. Higher priority instructions and approval boundaries remain authoritative.
When to Use
Use when an approved milestone, parent issue, bug, reframe phase, UI source, or execution slice needs a spec before planning or implementation. Explore first and ask second: inspect repo, tracker, artifact, and source evidence before asking, then ask only when intent/tradeoffs are undiscoverable. Load the selected slice plus 2-3 focused surfaces unless blocked.
Also use when the user says "deepen spec and run a technical review" or similar. Treat that as an explicit request to improve the existing canonical spec, apply professional technical review, repair fixable-now gaps, and rerun focused artifact-shape, BLUF, traceability, and validation gates before handoff. The long role-stack prompt beginning "You are GPT-5.5 acting as a senior software engineering reviewer, systems architect, implementation-risk analyst, specification maintainer, adversarial validation partner, and media artifact operator" is the same route for specs, with media/visual-reference evidence treated as an explicit review surface.
When Not to Use
Do not use for implementation, review-only feedback, task planning, runtime
install/sync, broad strategy, or unselected ideas. Stop when no selected slice
exists or when external writes, destructive changes, secret access, production
deployment, or broad repo edits lack approval.
If the supplied spec prompt still contains placeholders such as
[PASTE SPECIFICATION CONTENT OR SPEC PATH HERE], fail closed and request the
missing canonical spec path or content instead of drafting against a template.
Inputs
Required: problem statement, selected slice, and primary source evidence.
Optional: user-facing solution, user stories, implementation/testing decisions,
tracker metadata, QA report, current-vs-latest spec status, UI source,
session-collector evidence, .harness/** artifacts, and write approval.
What ships with it
7 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 Changed · +117 lines · +18 tokens per session bba424d49d0c
- 1mo ago First seen · 96 lines · 30 tokens per session scan A 4cc9b2d506a1
he-spec is a skill published in the GitHub repository jscraik/Agent-Skills (9 stars, last pushed 4d ago), licensed Apache-2.0. It adds 48 tokens to every session and 2,558 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-issue
Agent skill for swarm-issue - invoke with $agent-swarm-issue.
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…
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.
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.