obsigna general.instructions.md

Code-review instructions for a monorepo: one project containing several related packages, including software-development kits in Go, TypeScript, and Python. They focus on security, matching behavior across packages, and code quality.

In plain words
What is it for?
Use them when reviewing changes to signed records of AI-agent actions, especially changes to signing, hashing, JSON output, workflows, or shared SDK behavior.
Why use it?
They help reviewers catch leaked secrets, unsafe signing or data handling, inconsistent package behavior, and unfinished code.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/agent-receipts/obsigna/general
Clone the repo
git clone --depth 1 https://github.com/agent-receipts/obsigna

Made for: GitHub Copilot.

Per session 220 This file is loaded in full into every session.
When invoked 220 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00220 $0.00220
Opus 5 $0.00110 $0.00110
Sonnet 5 $0.00044 $0.00044
Haiku 4.5 $0.00022 $0.00022

Measured 2d ago against content hash 0591d05d2daa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

obsigna general.instructions.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.

.github/instructions/general.instructions.md · 26 lines

What it actually says

General review guidelines

This is the Agent Receipts monorepo — cryptographically signed audit trails for AI agent actions.

Security

  • Flag any real private keys, secrets, or credentials in the diff.
  • Ed25519 is the only supported signing algorithm. Flag any introduction of alternative or weaker schemes.
  • Parameters in receipts must be hashed (SHA-256), never stored in plaintext. Flag any plaintext parameter storage.
  • Flag any changes to .github/workflows/ — these require explicit maintainer review.

Cross-SDK consistency

  • Receipt output must be byte-identical across Go, TypeScript, and Python SDKs.
  • Changes to receipt creation, signing, hashing, or canonical JSON in any SDK should be flagged if there are no corresponding cross-language test updates.

Code quality

  • Flag unused code, dead imports, and breadcrumb comments ("moved to X", "removed").
  • Prefer first-principles fixes over bandaids.
  • Flag any TODO or FIXME comments that don't reference an issue number.
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.

  1. 2d ago First seen · 26 lines · 220 tokens per session scan A 0591d05d2daa

Subscribe to this mod's changes

obsigna general.instructions.md is an instructions file published in the GitHub repository agent-receipts/obsigna (20 stars, last pushed 3d ago), licensed Apache-2.0. It adds 220 tokens to every session, about $0.0011 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.