What is obsigna AGENTS.md?

Project instructions for Obsigna, a monorepo containing a signed audit-trail protocol, software libraries, an MCP proxy, hooks, integrations, tests, and documentation. An audit trail is a record of actions that can be checked for tampering.

Use them when working on Obsigna’s protocol, Go, TypeScript, or Python SDKs, proxy, hooks, integrations, documentation site, or cross-language tests.

They show where each component lives and which build and test commands apply to each programming language.

obsigna AGENTS.md — Instructions file by agent-receipts

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/agents-md

Clone the repo

git clone --depth 1 https://github.com/agent-receipts/obsigna

Made for: Codex, OpenCode.

Per session 1,712 This file is loaded in full into every session.

When invoked 1,712 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.

Model	Per session	Once invoked
Fable 5	$0.01712	$0.01712
Opus 5	$0.00856	$0.00856
Sonnet 5	$0.00342	$0.00342
Haiku 4.5	$0.00171	$0.00171

Measured 2d ago against content hash 9fb5bd56f40c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

obsigna 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.

AGENTS.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Monorepo for the Agent Receipts protocol — cryptographically signed audit trails for AI agent actions. Contains the protocol spec, SDKs in three languages, an MCP proxy, and the documentation site.

Monorepo layout

spec/          # Protocol specification and JSON schemas
sdk/go/        # Go SDK (receipt, store, taxonomy)
sdk/ts/        # TypeScript SDK (@obsigna/sdk-ts)
sdk/py/        # Python SDK (obsigna)
mcp-proxy/     # MCP STDIO proxy with audit, policy, and receipts (Go)
hook/          # PostToolUse hook binary for Claude Code and other runtimes (Go)
integrations/  # Per-agent-runtime adapters (e.g. opencode-plugin; hook to migrate here)
site/          # Documentation site (Astro)
cross-sdk-tests/  # Cross-language receipt verification tests
formal/        # Formal models (Alloy) machine-checking protocol properties

Each subdirectory has its own AGENTS.md with project-specific details.

Quick reference

Component	Language	Test command	Build command
sdk/go	Go	`go test ./...`	`go build ./...`
sdk/ts	TypeScript	`pnpm test`	`pnpm build`
sdk/py	Python	`uv run pytest`	`uv build`
mcp-proxy	Go	`go test ./...`	`go build ./cmd/...` (obsigna-mcp + mcp-proxy shim)
hook	Go	`go test ./...`	`go build ./cmd/...` (obsigna-hook + agent-receipts-hook shim)
site	TypeScript	—	`pnpm build`
spec	—	—	JSON schema validation

Operational state

Operational state lives at docs/operations/current.md. Read this first when starting a session. Update it when nodes change state.

Conventions

All changes go through pull requests — never push directly to main
CI is path-filtered: changes to sdk/go/ only trigger Go SDK CI
mcp-proxy CI also triggers on sdk/go/ changes (dependency)
hook CI also triggers on sdk/go/ changes (dependency)
Site deploys on site/** or spec/** changes
Go modules share a repo-root go.work (see Go workspace); never add a local replace directive in any published go.mod
Run language-specific linters before committing (go vet, biome, ruff)

Read the full file on GitHub · 135 lines

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.

2d ago First seen · 135 lines · 1,712 tokens per session scan A 9fb5bd56f40c

Subscribe to this mod's changes

obsigna AGENTS.md is an instructions file published in the GitHub repository agent-receipts/obsigna (20 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,712 tokens to every session, about $0.0086 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.

ai ai-agents audit cryptography ed25519

obsigna AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

Monorepo layout

Quick reference

Operational state

Conventions

What this file has done since we first saw it

Other instructions, from other repositories

warrant AGENTS.md

VCVio AGENTS.md

jentic-one GEMINI.md

briefloop AGENTS.md

MCPAudit AGENTS.md

agentlint AGENTS.md