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 ryan-scheinberg/harness --skill updating-ai-knowledgegit clone --depth 1 https://github.com/ryan-scheinberg/harnessWrote 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/ryan-scheinberg/harness/updating-ai-knowledge)<a href="https://agentmods.dev/skills/ryan-scheinberg/harness/updating-ai-knowledge"><img src="https://agentmods.dev/badge/skills/ryan-scheinberg/harness/updating-ai-knowledge.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 5.1 | $0.00079 | $0.01240 |
| Opus 5 | $0.00039 | $0.00620 |
| Sonnet 5 | $0.00016 | $0.00248 |
| Haiku 4.5 | $0.00008 | $0.00124 |
Grade A, and why
updating-ai-knowledge 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Is this worth updating?
Not every lesson belongs in a file. Before editing, pass these gates:
- Name the gap in one sentence. "This file says X, but the correct behavior is Y." If you can't say that, you don't have the fix yet — synthesize from what the session produced
- Would the next agent hit the same wall? If the problem was a one-off misread, a transient environment issue, or a one-time deploy workaround, the knowledge base isn't the problem
- Is the gap already covered somewhere? Search the target file first. Duplicating a rule in a second location creates two things to maintain and eventually contradicts
Stop if any gate fails. Not every session produces a knowledge update, and that's fine
Route to the right file
Work through these tests in order. The first match wins
Skill (~/Documents/harness/skills/)
Test: Would this fact be true in a different repo using the same tool or platform? If you swapped the repo but kept the tool, would the lesson still apply?
Cross-repo knowledge about tools, platforms, workflows. Group by skillset folder (project-skillset/, harness-skillset/). Run ./skills/install.sh from the harness repo root after adding or moving a skill directory
Guardrails: Don't change name: — tied to symlinks and the loader. Edit description: only if triggering is wrong (fires when it shouldn't, or doesn't fire when it should)
Examples: Jira skill has a wrong field name. Terraform module changed its variable interface
AGENTS.md (at the affected repo root)
Test: Is this fact specific to one repo's codebase, build, or local environment? Would it be meaningless or wrong if you pasted it into a different project?
Repo-specific context. Nearest file wins in nested structures; most agents read it automatically
Examples: Repo needs npm ci before tests. What a builder check covers here vs the full QA pass
Global CLAUDE.md (~/Documents/harness/CLAUDE.md, symlinked to ~/.claude/CLAUDE.md)
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.
- 8d ago First seen · 75 lines · 79 tokens per session scan A a3140b22ae79
updating-ai-knowledge is a skill published in the GitHub repository ryan-scheinberg/harness (2 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 1,240 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
gleanin
Rules distilled from past session friction (errors, edit loops, corrections), analyzed by a stronger model and applied to guide future work. Regenerated from glean/artifacts/ plus an index of trigger-loaded protocols from GLEANPROTOCOLDIRS by sync.sh — load every session via CLAUDE.md.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.