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/zigrivers/scaffold/agents-mdgit clone --depth 1 https://github.com/zigrivers/scaffoldWhat 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 | $0.00626 | $0.00626 |
| Opus 5 | $0.00313 | $0.00313 |
| Sonnet 5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
scaffold 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 yesterday.
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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
This repository does not use Beads for repo task tracking. Do not use the Beads CLI when working on Scaffold itself.
Quick Reference
make check # Run bash quality gates (lint + validate + test + eval)
make check-all # Run all quality gates (bash + TypeScript); full pre-push gate
git status -sb # Inspect local state quickly
git pull --rebase # Rebase onto latest remote state
git push # Publish local commits
Scaffold Releases
When releasing Scaffold itself, follow docs/architecture/operations-runbook.md
instead of the generic /scaffold:release guidance.
- Update
CHANGELOG.mdandREADME.mdwhen user-facing behavior, install or upgrade steps, migration instructions, or command semantics changed. - Merge the release-prep commit/PR to
mainbefore tagging. - Tag merged
mainasvX.Y.Zand push the tag. - Create the GitHub release.
publish.ymluses BOTH the GitHub OIDC trusted-publisher config (provenance signing only) AND theNPM_TOKENrepo secret (the actual registry PUT). As of v3.28.0 the OIDC token alone does NOT authorize the publish — if npm publish fails with auth errors, fix theNPM_TOKENsecret per docs/architecture/operations-runbook.md §4.2a, not the trusted-publisher config.- Verify the
publish.ymlandupdate-homebrew.ymlworkflows succeeded so users can update vianpm update -g @zigrivers/scaffoldandbrew upgrade scaffold.
Landing the Plane (Session Completion)
When ending a work session, you MUST complete ALL steps below. Work is NOT complete until git push succeeds.
MANDATORY WORKFLOW:
- File follow-up work - Record anything still needing work in the current tracker or leave explicit handoff notes
- Run quality gates (if code changed) - Run
make check-allas the full gate before push/hand-off - Update follow-up status - Make sure remaining work is reflected in the current tracker or handoff
- PUSH TO REMOTE - This is MANDATORY:
git pull --rebase git push git status # MUST show "up to date with origin" - Clean up - Clear stashes, prune remote branches
- Verify - All changes committed AND pushed
- Hand off - Provide context for next session
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.
- yesterday First seen · 60 lines · 626 tokens per session scan A 0d94a5a3df1f
scaffold AGENTS.md is an instructions file published in the GitHub repository zigrivers/scaffold (5 stars, last pushed yesterday), licensed MIT. It adds 626 tokens to every session, about $0.0031 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
drogon-claude-plugin CLAUDE.md
Claude Code instructions for voidvec/drogon-claude-plugin, covering drogon 后端开发规则, a. 异步回调模型（所有 handler 的最高纪律）, b. 事件循环模型（trantor io）, skill 路由表 and 通用纪律（跨 skill）.
speckit AGENTS.md
AGENTS.md instructions for jmanhype/speckit, covering agents.md - instructions for ai coding agents, core philosophy, pivotal methodology alignment, pivotal-style epic format and priority levels (pivotal-aligned).
speckit CLAUDE.md
Claude Code instructions for jmanhype/speckit, covering claude.md, repository structure, directory layout, pivotal labs methodology and pivotal-style beads workflow.
sdd CLAUDE.md
Claude Code instructions for LiorCohen/sdd, covering claude.md, task management rules (mandatory), output rules, git rules and build rules.
claude-code-templates CLAUDE.md
Instructions for Justdvp/claude-code-templates, covering claude.md, project overview, development commands, package management and application commands.
flow AGENTS.md
Instructions for cofin/flow: Flow is a toolkit for context-driven development. It has no flow executable; invoke the Flow skill or a /flow: command.