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/rockyhong/super-bootstrap/claude-mdgit clone --depth 1 https://github.com/RockyHong/super-bootstrapWrote 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/instructions/rockyhong/super-bootstrap/claude-md)<a href="https://agentmods.dev/instructions/rockyhong/super-bootstrap/claude-md"><img src="https://agentmods.dev/badge/instructions/rockyhong/super-bootstrap/claude-md.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 | $0.04400 | $0.04400 |
| Opus 5 | $0.02200 | $0.02200 |
| Sonnet 5 | $0.00880 | $0.00880 |
| Haiku 4.5 | $0.00440 | $0.00440 |
Grade A, and why
super-bootstrap CLAUDE.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 today.
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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
super-bootstrap
Development Workflow
Work enters by picking up a card — a docs/work/ card file (/super-bootstrap:todo pickup or a prose ID) — or grounding a new one via /super-bootstrap:log. The card is the grounding artifact (root-cause claim for a bug, problem statement for a feature) and the unit/anchor/boundary/SSOT of the change. Fresh work and resumed work use the same door.
The envelope
ground → route → implement → verify → doc-sync → commit. Red and verify are structurally empty — no ceremony — on a diff with no test/runtime surface (docs-only). Verify on a harness-file change (CLAUDE.md, rules, skills, agents) = audit-harness-edits. Commit = /super-bootstrap:commit.
Ambient laws inside implement:
- Test-first — where a test surface exists, a failing test precedes the implementation.
- Verify before claiming — evidence before "done / fixed / passing": run the check, read the output, then claim.
- Review received, not absorbed — check a review claim against the code before implementing it; disagree with grounds rather than complying performatively. Judgment-grade findings:
review-intakefirst (§ Dispatch).
Cluster routing
Recognize the card's shape, then take that row's discipline; a repo that installs a process harness maps its entries onto these shapes.
| # | Cluster | Route |
|---|---|---|
| 1 | Bug / broken behavior | root cause before fix — reproduce, trace to the mechanism, then change |
| 2 | Fuzzy feature / new capability | settle the design with the user before building |
| 3 | Design-intact multi-step | write the step sequence down before touching code |
| 4 | Refactor | ground the card; multi-step → cluster 3, atomic → envelope only |
| 5 | Config / taste / bounded tweak | inline; taste that iterates or drifts → card it |
| 6 | Docs / prose | envelope only |
| 7 | Harness edit | load-harness-principles pre, audit-harness-edits post |
| 8 | Triage / investigation-only | card → /super-bootstrap:triage {ID} (verdict phase appending a Verdict block to the card); ad-hoc question → inline reads + dispatched probes |
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.
- today Changed · +2 lines · +105 tokens per session 959c3a073487
- 5d ago First seen · 173 lines · 4,295 tokens per session scan A 6dd5c5cca212
super-bootstrap CLAUDE.md is an instructions file published in the GitHub repository RockyHong/super-bootstrap (3 stars, last pushed today), licensed MIT. It adds 4,400 tokens to every session, about $0.0220 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
recursive-decomposition-skill AGENTS.md
Instructions for massimodeluisa/recursive-decomposition-skill, covering agents: recursive-decomposition skill, read these first (mandatory), language policy, non-negotiables and commands.
qa-orchestra CLAUDE.md
Claude Code instructions for Anasss/qa-orchestra, covering qa orchestra — claude code instructions, what this project is, quick start, 1. clone into your workspace and 2. fill in your project context.
the-foundry AGENTS.md
AGENTS.md instructions for attac-t/the-foundry, covering the foundry, doctrine and rules.
swarms CLAUDE.md
Instructions for DheerG/swarms, a project described as: Achieve extraordinary results with claude code across a variety of tasks.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.