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/jrs1986/codingscaffold/agents-mdgit clone --depth 1 https://github.com/JRS1986/CodingScaffoldWhat 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 | $0.00868 | $0.00868 |
| Opus 5 | $0.00434 | $0.00434 |
| Sonnet 5 | $0.00174 | $0.00174 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
CodingScaffold 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents — CodingScaffold
This is the agent-context file for the CodingScaffold project itself. The constraints below apply to any AI coding agent working on this repo.
What this project is
A local-first, deterministic scaffold for AI-assisted coding teams. It is not a coding agent and never calls a model at runtime. Anything an agent contributes here should respect that posture.
Verification commands
Run these before claiming a change is done. Each must pass with exit code 0.
uv run ruff check— lint passes.uv run pytest -q— full test suite passes (330+ tests as of v0.5.0).
For larger changes, also run the scaffold on itself as a smoke check:
coding-scaffold context lint --target .— must pass with no errors.coding-scaffold eval run --target .— must pass.
The repo ships an .coding-scaffold/eval-config.json that disables the checks for
policy_exists and denied_files_configured because this repo deliberately ships no
policy pack and no agent-permissions.json (see "Deliberately absent" below).
Project constraints
- No new runtime dependencies.
pyproject.toml'sdependencies = []is intentional. Dev-only deps go in[project.optional-dependencies].devand must justify their weight. - No LLM calls. The scaffold is deterministic by design; pytest verifies this by running offline. Any feature that wants an LLM is the coding tool's responsibility.
- No network calls. The only allowed subprocess is
git. Adding any other network egress requires an explicit design discussion in the PR. - No telemetry. Ever.
- Backwards compatibility. Every existing CLI command should keep working unless a breaking change is explicitly called out in the PR title and the CHANGELOG.
Commit messages
Plain, descriptive commits. Do not append a Co-Authored-By: Claude ... trailer.
Session traces for bigger changes
For PRs that touch three or more modules, or for any architectural change, start a session trace so reviewers can follow the steps without re-running the agent in their head:
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 · 85 lines · 868 tokens per session scan A 6b4d4b1fe8d1
CodingScaffold AGENTS.md is an instructions file published in the GitHub repository JRS1986/CodingScaffold (9 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 868 tokens to every session, about $0.0043 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
Atomic-Spec AGENTS.md
Instructions for Chappygo-OS/Atomic-Spec, covering agents.md — adding a new ai agent to atomic spec, about atomic spec and the atomicspec cli, general practices, adding new agent support and current supported agents.
leashd CLAUDE.md
Instructions for vmehera123/leashd, covering claude.md, commands, install dependencies, run tests (single file / specific test / all) and run tests with coverage.
claude-skills CLAUDE.md
Instructions for mastepanoski/claude-skills, covering claude.md, repository purpose, testing skills locally, repository architecture and core structure.
AmbyKit CLAUDE.md
Instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.
learn-likecc AGENTS.md
AGENTS.md instructions for Harzva/learn-likecc, a project described as: Claude Code 源码逆向恢复项目 | Source Map 逆向 · 架构分析 · 可运行版本 | 1900+ 文件 · 51万行代码 · 12章节课程.
AIWiki CLAUDE.md
Claude Code instructions for XuebinMa/AIWiki, covering claude.md — aiwiki 项目记忆, 这是什么, 每次动手前必读（按顺序）, 写作 / 翻译用 skill（不要手搓流程） and 保持连贯的硬规则（防止跨会话的风格 / 内容漂移）.