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 define-projectgit 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/define-project)<a href="https://agentmods.dev/skills/ryan-scheinberg/harness/define-project"><img src="https://agentmods.dev/badge/skills/ryan-scheinberg/harness/define-project/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/ryan-scheinberg/harness/define-project"><img src="https://agentmods.dev/badge/skills/ryan-scheinberg/harness/define-project.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 | $0.00067 | $0.00573 |
| Opus 5.5 | $0.00027 | $0.00229 |
| Sonnet 5.5 | $0.00013 | $0.00115 |
| Haiku 4.5 | $0.00007 | $0.00057 |
Grade A, and why
define-project 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Produce a PROJECT_BRIEF.md proficient agents can pick up and build from without clarifying questions. Terse, opinionated, decisions made not deferred. The user's persona and preferences already live in CLAUDE.md — don't restate them
Process
- Read the user's input. Infer what you can as an architect.
iterate-plancloses the rest after the first draft - Explore the codebase if one exists starting with
AGENTS.mdfiles. Tech stack, test setup, CI, module boundaries, naming conventions. Don't ask what code can answer - Decide. Pick the stack and scope the MVP — the thinnest end-to-end vertical path that proves the approach. Genuine uncertainty goes in Risks & Open Questions. Default to deciding. Hedged briefs ship ambiguity forward into dev turns. Don't name downstream slices here — that's
plan-to-slices' job, and pre-slicing the brief locks in a shape before the MVP has taught you anything - Write the brief using the template. Adapt freely — drop sections that don't apply, add sections when the project needs them. A bug fix doesn't need a business model; a SaaS needs all of it
Template
[Project Name]
Context
What this is, why it exists, the problem it solves. No throat-clearing
Audience
Who uses or benefits. For internal or infra work this may be "the deployment pipeline" or "future contributors to this repo"
Scope
The MVP Slice
One sentence: "A user/system can [do X] and [see/get Y]"
In Scope
- ...
Out of Scope
- What's excluded and why
Technical Approach
Stack, architecture, data, auth, infra with rationale. For existing codebases: what changes, what doesn't
Testing & Observability
What gets tested and instrumented. Structured logging, key metrics, health checks. What tells you this is working or broken in prod
Deployment & Rollout
Environments, rollout strategy, flags, rollback. Skip for non-deployable work
Risks & Open Questions
What's uncertain. Each item notes what would close it
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 · 55 lines · 67 tokens per session scan A de8b5a33066b
define-project is a skill published in the GitHub repository ryan-scheinberg/harness (2 stars, last pushed 3mo ago), licensed MIT. It adds 67 tokens to every session and 573 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
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
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports 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…
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.
design-review
Review a web app or page for visual design quality — layout, typography, spacing, colour, hierarchy, consistency, interaction patterns, and responsive behaviour. Not a UX audit (that checks usability) — this checks whether it looks professional and polished. Produces a design findings report with screenshots.…
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.