covenant

covenant is a command for Claude Code from sonicfieldlabs/akouo. It costs 0 tokens per session (832 once invoked), scanned A, original, MIT.

A command for applying a human-written listening policy before or during audio capture. The policy can define what may be heard, retained, revealed, blurred, or refused, including time-based restrictions.

In plain words
What is it for?
Use it to load or verify a listening policy, run listening under that policy, audit an earlier hearing, explain the policy’s effects, and record its ethical conditions.
Why use it?
It helps protect a person’s, household’s, or community’s rules about privacy and consent. It also records which restrictions were enforced when a hearing took place.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it to load or verify a listening policy, run listening under that policy, audit an earlier hearing, explain the policy’s effects, and record its ethical conditions.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/sonicfieldlabs/akouo/covenant
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.

Clone the repo
git clone --depth 1 https://github.com/sonicfieldlabs/akouo

Made for: Claude Code.

Wrote 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.

agentmods badge for covenant

README.md
[![agentmods](https://agentmods.dev/badge/commands/sonicfieldlabs/akouo/covenant/github.svg)](https://agentmods.dev/commands/sonicfieldlabs/akouo/covenant)
Your own site
<a href="https://agentmods.dev/commands/sonicfieldlabs/akouo/covenant"><img src="https://agentmods.dev/badge/commands/sonicfieldlabs/akouo/covenant/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for covenant

Your own site · 80×15
<a href="https://agentmods.dev/commands/sonicfieldlabs/akouo/covenant"><img src="https://agentmods.dev/badge/commands/sonicfieldlabs/akouo/covenant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 832 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00832
Opus 5.5 $0.00000 $0.00333
Sonnet 5.5 $0.00000 $0.00166
Haiku 4.5 $0.00000 $0.00083

Measured 23d ago against content hash 091162f5988e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

covenant 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 23d 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.

commands/covenant.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/covenant

Purpose

/covenant is the sovereignty command of akoúō. Its parties author the covenant and the owner applies the adopted revision. The command reports which supported rules were checked, which material was withheld, and which terms remain interpretive commitments.

Use it when the listening answers to someone: a person's right to silence, a household's retention rules, a community's protocol for ancestral or place-bound sound, a habitat's "and not one decibel more."

When To Use

Use /covenant for:

  • listening under an active covenant and reporting its effects honestly
  • adopting, inspecting, or verifying a covenant before any capture happens
  • auditing a prior hearing (own or another agent's) against a declared covenant
  • explaining a covenant back to its author: which lines the engine enforces, which it carries as commitments
  • registering a hearing whose memory record must say under which ethics it was listened

The default of every chain is NO covenant: sovereignty is opted into by the operator, never imposed by the tool. /covenant with no covenant available reports exactly that and stops.

Skills Called

  • akouo-router
  • sovereign-listening (primary)
  • acoulogical-object-listening (secondary)
  • signal-inspection-listening (corrective)

Execution Order

  1. Run akouo-router; the covenant's existence, identity, and enforcement surface are part of the evidence inventory.
  2. Run sovereign-listening: verify the covenant (id, version, sha256, lineage), apply pre-capture rules, and declare which rules the host's gates enforce.
  3. Run acoulogical-object-listening on what the covenant admits — the allowed material deserves a full perceptual description on its own terms.
  4. Run signal-inspection-listening as corrective: measured claims about the remaining material stay measured.
  5. Synthesize; populate the output's covenant block (identity + withheld list + commitments count) and what_remains_hidden with withheld categories. When the host will store the hearing, the memory record carries the covenant's identity (spec v1.3 covenant block in akousma stores).

Read the full file on GitHub · 68 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.

  1. 23d ago Changed · +15 lines 091162f5988e
  2. 2mo ago First seen · 53 lines · 0 tokens per session scan A 99e184d21fcc

Subscribe to this mod's changes

covenant is a command published in the GitHub repository sonicfieldlabs/akouo (10 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 832 tokens. 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.

Related

covenant compared with commands from other repositories

covenant next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
covenantsonicfieldlabs/akouoCommand102d agoMITA0Claude Code
checklistgithub/spec-kitCommand148kyesterdayMITA13Claude Code
clarifygithub/spec-kitCommand148kyesterdayMITA27Claude Code
specifygithub/spec-kitCommand148kyesterdayMITA13Claude Code
analyzegithub/spec-kitCommand148kyesterdayMITA26Claude Code
convergegithub/spec-kitCommand148kyesterdayMITA35Claude Code
implementgithub/spec-kitCommand148kyesterdayMITA14Claude Code