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/bitmask-stack/carbonado/agents-mdgit clone --depth 1 https://github.com/bitmask-stack/carbonadoWhat 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 | $0.19385 | $0.19385 |
| Opus 5 | $0.09692 | $0.09692 |
| Sonnet 5 | $0.03877 | $0.03877 |
| Haiku 4.5 | $0.01938 | $0.01938 |
Grade A, and why
carbonado 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 — 982 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Carbonado Development Guidelines
Project: Carbonado (bitmask-stack/carbonado)
Mission: Apocalypse-resistant archival format for consensus-critical data, with a focus on Bitcoin quantum resistance.
Current Status (as of 2026-07): Symmetric v2 stack (CARBONADO20\n, AES-256-CTR + HMAC-SHA512 EtM) stable. P1: SLICE_LEN=4096, keyed 4 KiB Bao groups, seekable slice verify. P2: streaming-first encode/decode. P3: segment sharding. P4: Adamantine 1.0 directory archives (see §7.1). FEC: reed-solomon-erasure RS 4/8. Outboard + scrub complete.
Unified streaming stack (three independent axes — do not conflate):
| Axis | Status |
|---|---|
| Streaming / memory | Phase 1 fused sync path shipped (SeekableSpool, streaming EtM, stripe FEC). M1: non-FEC verification (c6) uses SeekWriteAt (O(chunk) RAM); FEC verification retains O(FEC body) shard buffers under segment-wide RS geometry (finish_into avoids a second full logical Vec). Residuals: FEC O(segment body), O(sidecar) outboard verify, async encoded-body spool. See doc/STREAMING_PARALLELISM.md. Not the same as Bao slice/stream verification. |
| Concurrency | Phase 2 optional async / stream_decode_async (disk spool bridge; WASM NotImplemented). |
| Parallelism | Phase 3 parallel feature (default on): std::thread::scope RS parity; WASM serial at runtime. No rayon; Tokio is not the CPU-parallel story. |
PQC: bitcoinpqc 0.4, SLH-DSA-SHA2-128s sidecars only (SLH_DSA_SHA2_128S). Dev SHAKE-128s sidecars are incompatible — re-sign.
1. Core Principles
- Clean cryptographic break. This version of Carbonado does not contain any code to read or write v1 ECIES-encrypted files. Old encrypted archives require external migration (use an older version of the tool to extract plaintext, then re-encode with the new symmetric primitives).
- "Backward compatibility / migration path" (from the original spec) refers only to preserving the non-crypto properties of the format:
- Pipeline ordering (compress(zstd-20) → encrypt → FEC → bao and reverse)
- Flat-file portability
- WASM/browser support
- Bao-based streaming verification and replication proofs
- Forward error correction (4/8 RS model — see v1-vs-v2 rationale)
- Content addressability via the outer bao hash
- First-principles security. All cryptographic decisions must be justifiable from security definitions (IND-CPA for CTR, INT-CTXT for EtM, PRF properties of HMAC-SHA512, domain separation, key independence).
- HMAC-SHA512 is mandatory for both authentication (full 64-byte tags) and all subkey derivation. No simple splits, no SHA-256-only KDFs for key material.
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 · 982 lines · 19,385 tokens per session scan A eccb79c6cd2e
carbonado AGENTS.md is an instructions file published in the GitHub repository bitmask-stack/carbonado (119 stars, last pushed 4d ago), licensed MIT. It adds 19,385 tokens to every session, about $0.0969 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 2026-08-30.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.