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 instructions/seven128/project-tiny-context-harness/agents-mdgit clone --depth 1 https://github.com/Seven128/project-tiny-context-harnessWhat 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 | $0.05179 | $0.05179 |
| Opus 5 | $0.02589 | $0.02589 |
| Sonnet 5 | $0.01036 | $0.01036 |
| Haiku 4.5 | $0.00518 | $0.00518 |
Grade A, and why
project-tiny-context-harness AGENTS.md 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 2d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Agent Overlay
本文件是 agent 启动路由器和硬边界,不承载完整设计思想、长原则或角色流程;默认 Minimal Context 规则见下方 managed block。
本仓库 Authoring 例外
- 本仓库维护
project-tiny-context-harnesspackage、Minimal Context managed assets、source sync、validator 和 delivery benchmark。 - 本仓库开发可由用户或当前 Goal 选择临时 task branch/worktree;提交可按可读性保留,开发噪声可在分支内 squash。显式
long-task-workflow仍只复用用户选定的验证工作区,Harness 不创建编排分支、Worker 或 worktree。 - 使用临时分支的交付最终必须回归干净且与
origin/main同步的main,并让最终分支 tip 通过 fast-forward 或 merge commit 成为origin/main的祖先或与其相等,再删除对应本地/远端分支。ahead、diverged、脏或未知 worktree 阻止清理;普通治理不用git branch -D。日常收尾只清理本任务分支,清理全部非main分支必须是显式仓库级治理请求。 - 修改
packages/ty-context/**、.codex/ty-context-managed/**、tools/**或examples/delivery-benchmark/**时,先读 core Context、default area root 和由project_context/context.toml触发的相关 on-demand Context,并使用.codex/skills/authoring/harness_package_design/SKILL.md。 - 旧阶段式工作流只作为历史设计摘要保留在
PROJECT_SPEC.md;不要把 stage artifacts 恢复成默认 package 能力。 - Karpathy 编码准则是本仓库 agent 的底层行为原则:先思考并暴露假设,优先简洁,精准修改,目标驱动验证;不要把长原则常驻在 AGENTS 启动路径。
Minimal Context Harness Protocol
This project uses Tiny Context. The Harness maintains durable Context and workflow authority; project tests, CI, runtime evidence and human acceptance prove product quality. Its three capabilities are Minimal Context, the automatically applicable model-led default Workflow Contract for work of any complexity and the explicitly selected Single-Goal Long-Task Workflow for machine completion authority, recoverability and auditability. Complexity determines execution and verification depth; required completion authority and recoverability determine the workflow route; Long-Task-internal risk determines proof strength.
Shared Engineering Quality Obligation
Before the first implementation edit, every delivery surfaces one externally observable, repository-bound Architecture Deliberation. Depth is risk-proportional, but the checkpoint always names affected owners, the current extension point/source of truth, dependency and state/lifecycle boundaries, the selected design and material alternatives, one plausible future-change challenge, touched technical debt and its disposition, forbidden shortcuts, project-owned checks and triggered engineering-quality attributes or their concrete preservation basis. Correctness/invariants and maintainability/changeability always receive at least a preservation judgment; reliability/resource lifecycle, concurrency/consistency, performance/capacity/cost, security/privacy/safety, compatibility/migration/rollout and operability/observability/testability activate only when the change or an explicit claim makes them material. Exact product/technical predicates remain owned by Semantic Facts and exact selected UI/UX values by selected-design closure. Refresh the checkpoint when scope, ownership, selected design, quality applicability or debt disposition materially changes.
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.
- 2d ago First seen · 106 lines · 5,179 tokens per session scan A b3b5871e1b5b
project-tiny-context-harness AGENTS.md is an instructions file published in the GitHub repository Seven128/project-tiny-context-harness (3 stars, last pushed 2d ago), licensed MIT. It adds 5,179 tokens to every session, about $0.0259 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 instructions, from other repositories
fastagent AGENTS.md
Instructions for fastagent-sh/fastagent, covering fastagent — agent guide, what this is, source of truth, repo map and devx principle stack.
trellis AGENTS.md
Instructions for craigcossairt/trellis, covering agents.md , project, what i need from agents, current state - source of truth pointers and tech stack.
scopeglass AGENTS.md
Instructions for zackabrah/scopeglass, covering scopeglass contributor instructions, project, commands, conventions and boundaries.
agentic-coding-workflow AGENTS.md
Instructions for abhilash-m96/agentic-coding-workflow, covering agentic coding workflow, rules, step 1 — understand the full scope, step 2 — propose the chunk plan and step 3 — write the finalised plan.
android-qa-kit AGENTS.md
Instructions for willbytee-sudo/android-qa-kit, covering agents.md — setting up and driving an android device, 1. how to work with the user, 2. start by finding out what's already there, 3. what you can do in each mode and 4. if there's no device: ask first.
agentscribe copilot-instructions.md
Instructions for Lucabiz/agentscribe, covering agentscribe, setup & commands, code style & conventions, testing and do not.