Borrowing it
Nothing to install: this file belongs to Seven128/project-tiny-context-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Seven128/project-tiny-context-harness/main/.codex/skills/authoring/harness_package_design/SKILL.mdgit clone --depth 1 https://github.com/Seven128/project-tiny-context-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/seven128/project-tiny-context-harness/harness_package_design)<a href="https://agentmods.dev/skills/seven128/project-tiny-context-harness/harness_package_design"><img src="https://agentmods.dev/badge/skills/seven128/project-tiny-context-harness/harness_package_design.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 | $0.00040 | $0.01014 |
| Opus 5 | $0.00020 | $0.00507 |
| Sonnet 5 | $0.00008 | $0.00203 |
| Haiku 4.5 | $0.00004 | $0.00101 |
Grade A, and why
harness_package_design 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 6d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Package Design Authoring
Maintain this repository as the source workspace for Project Tiny Context Harness. The product keeps project_context/** as the smallest durable project fact source, supplies the automatically applicable default Workflow Contract, and optionally supplies one Single-Goal Long-Task authority path. Harness maintains Context and workflow mechanisms; project code, tests, runtime evidence, CI and human acceptance prove product quality.
This authoring Skill is repository-local. Never copy .codex/skills/authoring/** into consumer package assets. A rule that belongs in every consumer must reach its actual managed source, package asset, public guidance, Context and tests through the normal source-sync path.
Always establish
- Follow root
AGENTS.md; read core Context, the default area and triggered owning Context before deciding the change. - Separate current implementation truth from intended product truth. Index the real owner, managed source, generated/install surface, package asset, public docs, tests, migration and release impact. Do not patch only the first failing copy.
- Before the first implementation edit, surface the repository-bound Architecture Deliberation required by the default Workflow Contract and choose exactly one
Context Delta: none|required. Durable mechanism or distribution meaning is normallyrequiredand reaches owning Context before code. - Preserve Minimal Context: no stage artifact chain, second Authority, second plan, second Gate, lifecycle, scheduler, registry or persistent orchestration state unless an explicit project-owner decision changes that boundary.
- Keep public package surfaces English-complete. Non-English triggers/examples are additive and require an equivalent narrow English path plus drift coverage.
- Make mechanism changes in the mechanism owner and prove them with current-candidate project checks. Documentation and tests cannot jointly redefine absent runtime behavior.
Scope / Cost Drift Stop
What ships with it
5 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.
- 6d ago First seen · 51 lines · 40 tokens per session scan A 87d52eed7627
harness_package_design is a skill published in the GitHub repository Seven128/project-tiny-context-harness (3 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 1,014 once invoked, about $0.0002 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
agentic-code-review
Use when reviewing a diff, pull request, branch, or AI-generated code for correctness, security, regression, test, performance, and maintainability risks before merge.
hooksmith
Use when designing or reviewing safe Grok Build hooks for linting, tests, formatting, notifications, command guards, lifecycle automation, or project hook trust decisions.
repo-health-check
Use when auditing a repo before changes to find the smallest safe PR, quality risks, stale docs, missing tests, ignored-file gaps, or agent setup issues. Best first skill for unfamiliar codebases.
architecture-review
Use for clean architecture, modular monoliths, hexagonal boundaries, service boundaries, data flow, dependency direction, ADRs, or large feature planning.
frontend-ux-engineer
Use for frontend features, Next.js/React/Vue/Svelte UI, accessibility, responsive layout, design polish, state handling, forms, visual QA, or product workflow improvements.
git-github-flow
Use for branch prep, clean commits, PR descriptions, GitHub issue triage, changelogs, release notes, review response, merge readiness, or publishing a branch safely.