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 agentmods add skills/mifunedev/openharness/wikinpx skills add mifunedev/openharness --skill wikigit clone --depth 1 https://github.com/mifunedev/openharnessWrote 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/mifunedev/openharness/wiki)<a href="https://agentmods.dev/skills/mifunedev/openharness/wiki"><img src="https://agentmods.dev/badge/skills/mifunedev/openharness/wiki.svg" alt="Measured on agentmods" 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 | $0.00219 | $0.01404 |
| Opus 5 | $0.00110 | $0.00702 |
| Sonnet 5 | $0.00044 | $0.00281 |
| Haiku 4.5 | $0.00022 | $0.00140 |
Grade A, and why
wiki 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 3d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki
One parameterized skill over the harness wiki knowledge base. The first token of
$ARGUMENTS selects the operation; the remainder is that subcommand's argument
string. This dispatcher holds the routing logic and the rules shared by all
three operations; the full per-subcommand procedure lives in references/.
Subcommands
| Subcommand | Argument form | Purpose | Reference |
|---|---|---|---|
ingest |
<url|path> [--slug <override>] · --from-draft <slug> [--allow-stale] |
Capture a source or promote a draft into a wiki entity page (the only authorized write path) | references/ingest.md |
query |
<topic> |
Frontmatter OR-search; read top ≤3 matches (by updated: desc) into context |
references/query.md |
lint |
[--dry-run] |
5 health checks + atomic corpus/README.md index regeneration |
references/lint.md |
Dispatch
Parse $ARGUMENTS: the first whitespace-delimited token is the subcommand; the
rest is the subcommand's argument string.
ARGUMENTS="${ARGUMENTS:-}"
SUB="${ARGUMENTS%% *}" # first token
REST="${ARGUMENTS#"$SUB"}" # everything after it
REST="${REST# }" # trim one leading space
Route on $SUB, then follow the matching reference document end-to-end (its
instructions are authoritative — this dispatcher does not restate them):
$SUB |
Action |
|---|---|
ingest |
Read references/ingest.md; execute it with $REST as its argument string. |
query |
Read references/query.md; execute it with $REST as the <topic>. |
lint |
Read references/lint.md; execute it with $REST (only --dry-run is recognized). |
| anything else (incl. empty) | Print the usage line from argument-hint and exit 0. Do not guess a subcommand. |
Shared rules
These hold across all three subcommands; the reference docs assume them.
- Corpus root: entity pages at
.oh/skills/wiki/corpus/<slug>.md; immutable snapshots at.oh/skills/wiki/corpus/raw/<yyyy-mm-dd>-<slug>.md. Create.oh/skills/wiki/corpus/raw/before any write — it is gitignored and may be absent on a fresh clone. - Gitignore-by-default:
.oh/skills/wiki/corpus/*is gitignored; the operator whitelists a curated entry into git withgit add -f <entry>.corpus/README.mdandcorpus/raw/README.mdare tracked directory anchors. A local-only scratch entry never breaks CI — the README index and thewiki-readme-index.shprobe are both built from the git-tracked entry set only. - Canonical schema: frontmatter fields, body layout, slug derivation, the
≤600-word cap, cross-link convention, confidence lifecycle, and the body-merge
strategy all live in
.oh/skills/wiki/references/schema.md. The reference docs and this dispatcher defer to it — they never redefine it. - Frontmatter extraction (canonical, used identically by
queryandlint):awk '/^---$/{f=!f; next} f{print}' .oh/skills/wiki/corpus/<slug>.md - Orchestrator-only write gate:
ingestwrites (snapshots + entity pages) andlint'scorpus/README.mdregeneration are orchestrator-only. Sub-agents propose drafts to$TMPDIR/oh-wiki-drafts/<slug>.md; the orchestrator promotes via/wiki ingest --from-draft <slug>. A sub-agent that writes directly to the corpus is out of scope and may be reverted. - Index reflects tracked entries:
corpus/README.md's Index table is generated state owned bylint, sorted byupdated:descending. Never hand-edit it.
What ships with it
33 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.
- corpus/audit-architecture.md 4.1 KB
- corpus/crabbox-remote-exec-control-plane.md 3.9 KB
- corpus/document-ingestion.md 3.9 KB
- corpus/fresh-machine-setup.md 5.2 KB
- corpus/managed-agents.md 5.3 KB
- corpus/molt-agentic-reinforcement-learning.md 6.2 KB
- corpus/oh-cli-portable-lifecycle.md 8.4 KB
- corpus/plan-vs-built-reconciliation.md 5.4 KB
- corpus/prime-agent-harness.md 4.8 KB
- corpus/raw/2026-06-27-recursive-language-models.md 3.8 KB
- corpus/raw/2026-07-04-crabbox-remote-exec-control-plane.md 4.6 KB
- corpus/raw/2026-07-04-runtime-isolation-landscape.md 3.5 KB
- corpus/raw/2026-07-17-audit-architecture.md 446 B
- corpus/raw/2026-07-18-markitdown.md 15 KB
- corpus/raw/2026-08-12-build-executor-ladder.md 7.6 KB
- corpus/raw/2026-08-23-release-versioning.md 6.9 KB
- corpus/raw/2026-08-24-plan-vs-built-reconciliation.md 5.3 KB
- corpus/raw/2026-08-26-prime-agent-harness.md 5.6 KB
- corpus/raw/README.md 1.2 KB
- corpus/README.md 4.4 KB
- corpus/recursive-language-models.md 4.4 KB
- corpus/recursive-self-improvement-survey.md 4.5 KB
- corpus/release-versioning.md 5.6 KB
- corpus/runtime-isolation-landscape.md 3.7 KB
- corpus/sandbox-dependency-installs.md 5.8 KB
- references/concurrent-ingest-worktrees.md 1.3 KB
- references/github-repo-research-wiki.md 2.7 KB
- references/ingest.md 38 KB
- references/lint.md 17 KB
- references/official-docs-research-wiki.md 2.1 KB
- references/query.md 8.3 KB
- references/schema.md 14 KB
- references/social-image-wiki-ingest.md 1.9 KB
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.
- 3d ago First seen · 99 lines · 219 tokens per session scan A 290ead629df9
wiki is a skill published in the GitHub repository mifunedev/openharness (36 stars, last pushed 3d ago), licensed Apache-2.0. It adds 219 tokens to every session and 1,404 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
data-visualization
Use for creating publication-quality charts and multi-panel analysis summaries. Triggers when tasks involve visualizing data, plotting results, creating charts, or producing visual reports from analysis output.
cuml-machine-learning
Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.
blog-post
Writes and structures long-form blog posts, creates tutorial outlines, and optimizes content for SEO with cover image generation. Use when the user asks to write a blog post, article, how-to guide, tutorial, technical writeup, thought leadership piece, or long-form content.
social-media
Drafts engaging social media posts, writes hooks, suggests hashtags, creates thread structures, and generates companion images. Use when the user asks to write a LinkedIn post, tweet, Twitter/X thread, social media caption, social post, or repurpose content for social platforms.
remember
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…
textual-screenshot
Capture a Textual terminal UI as an SVG using its headless test harness. Use when asked to make, attach, or preview a screenshot of deepagents-code/dcode or another Textual app, visually verify a TUI state, or render a modal, screen, or widget without a desktop or browser.