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 gaia-research/gaia-skill-heaven --skill harness-door-patterngit clone --depth 1 https://github.com/gaia-research/gaia-skill-heavenWrote 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/gaia-research/gaia-skill-heaven/harness-door-pattern)<a href="https://agentmods.dev/skills/gaia-research/gaia-skill-heaven/harness-door-pattern"><img src="https://agentmods.dev/badge/skills/gaia-research/gaia-skill-heaven/harness-door-pattern/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/gaia-research/gaia-skill-heaven/harness-door-pattern"><img src="https://agentmods.dev/badge/skills/gaia-research/gaia-skill-heaven/harness-door-pattern.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 | $0.00076 | $0.02381 |
| Opus 5.5 | $0.00030 | $0.00952 |
| Sonnet 5.5 | $0.00015 | $0.00476 |
| Haiku 4.5 | $0.00008 | $0.00238 |
Grade A, and why
harness-door-pattern 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Harness Door Pattern
A door boots a harness into a chosen posture. Five have been built. The work is the same shape every time, and most of the cost is in the probe, not the code.
This skill exists so door six is cheap.
The core insight
Every harness hides its skills somewhere different, but there are only about four places. Identify which class you are dealing with and you have most of the answer. Guess wrong and you will burn a probe campaign proving a flag does nothing.
Class 1 — Allowlist flags that read like suppression flags
The flag takes a list of scopes to load. Naming a scope keeps it alive. The instinct to "name the thing you want to suppress" is exactly backwards, and it looks correct in a diff.
| harness | flag | the trap |
|---|---|---|
| claude | --setting-sources |
naming project keeps project-scope skills. Empty string is the suppression. |
| hermes | --toolsets |
naming a set that omits skills is what drops the skill index. |
This class has bitten twice in this repo — KC4 on curated, then P8 on product-floor (#24),
which shipped with the same defect for a month because the fix was applied to one posture and
not its sibling. When you fix an allowlist, grep for every other posture using the same flag.
Class 2 — Native evict / readmit
The harness has a real primitive: one flag clears skills, another admits specific ones. Cleanest class to build against; a curated posture falls out almost for free.
| harness | evict | readmit |
|---|---|---|
| pi | --no-skills |
--skill <path> (repeatable, takes a path) |
Class 3 — Config-home scoping
An env var relocates the harness's whole config root. Point it at the session dir and the harness sees an empty world.
| harness | var |
|---|---|
| codex | CODEX_HOME |
| hermes | HERMES_HOME |
| grok | GROK_HOME |
The auth trap — this has cost time on every harness in this class. A scoped config home has
no credentials, so the session cannot authenticate and every probe fails in a way that looks
like the suppression broke. Copy auth.json (or equivalent) in via an fsPlan
copyFileIfExists before concluding anything. compileCodex() is the reference.
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 · 197 lines · 76 tokens per session scan A 2468a8084cac
harness-door-pattern is a skill published in the GitHub repository gaia-research/gaia-skill-heaven (4 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 2,381 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
architecture-compass
Architectural thinking partner for an existing repository — scans the codebase, conducts a structured interview, agrees on current architectural state and recommended direction, and produces a shareable insights document. Scoped to one repository, module, or folder. Does not execute transformation — it orients. Use…
skill-review
Deep behavioral audit of a Lattice skill — proposes 3 review personas relevant to the skill, runs independent scenario analysis from each persona's perspective, then merges only the high-confidence, practical findings into a severity-ordered gap report with proposed fixes. Structural validation (conventions…
architecture-refiner
Facilitate a structured conversation to define architecture principles for a repository. Supports multiple architecture styles: clean architecture (default), hexagonal / ports & adapters, modular monolith, or custom. Produces a formal architecture document that the corresponding atom will use. Use when setting up a…
clean-code-refiner
Facilitate a structured conversation to define clean code principles for a repository. Produces a formal clean-code.md document that the clean-code atom will use as its override. Use when setting up coding standards, defining code quality rules, or when the user says 'setup clean code', 'define coding standards'…
review-refiner
Facilitate a structured conversation to customize how the review molecule works -- atom loading rules, severity classification, report format, scope rules, insight capture, and health logging. Produces a formal review-standards.md document that the review molecule will use as its process configuration. Use when the…
review
Perform a structured code review by composing validation checklists from relevant atoms based on what code changed. Loads atoms conditionally -- clean-code always, architecture/DDD/security/tests only when the delta touches their domain. Produces a severity-ordered report with specific locations and fixes. Use when…