What is Aletheia CLAUDE.md?

A repository instruction file for Aletheia, an application and its development and testing workspace, covering project rules and commands.

Use it when maintaining Aletheia, running its tests and confidentiality scan, checking a coprocessor, or rebuilding its Codex and Cowork packages.

It tells coding agents where the main governance rules live and which checks to run before changing or rebuilding the project.

How nsankar/Aletheia configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to nsankar/Aletheia. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/nsankar/Aletheia/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/nsankar/Aletheia

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/nsankar/aletheia/claude-md/github.svg)](https://agentmods.dev/instructions/nsankar/aletheia/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/nsankar/aletheia/claude-md"><img src="https://agentmods.dev/badge/instructions/nsankar/aletheia/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/nsankar/aletheia/claude-md"><img src="https://agentmods.dev/badge/instructions/nsankar/aletheia/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,099 This file is loaded in full into every session.

When invoked 1,099 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01099	$0.01099
Opus 5.5	$0.00440	$0.00440
Sonnet 5.5	$0.00220	$0.00220
Haiku 4.5	$0.00110	$0.00110

Measured 2mo ago against content hash 0bf593139ae1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Aletheia 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 2mo 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.

CLAUDE.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@AGENTS.md

Claude Code — project instructions (Aletheia)

AGENTS.md, imported above, is the sole behavioral governance source: Aletheia's identity, the Constitution (I1–I13), epistemic character, self-tuning discipline, and engagement rules. Do not restate or extend governance in this file; edit AGENTS.md (operator action only, per I12). This file covers repository operations only.

Repository role

This repo is simultaneously (a) the deployed Aletheia product and (b) its development and test workshop. Which mode applies to a given request is decided by the operator vs. end user rules in AGENTS.md — an investigation question gets a Verdict; maintenance work on Aletheia itself gets normal engineering collaboration.

Commands

Task	Command
Full test suite (must stay green; 33 tests + 1 skip)	`python -m pytest tests/ -q`
Confidentiality scan on any outward-facing text	`python tests/leak_scan.py <file>`
Coprocessor sanity check	`python .claude/skills/aletheia/scripts/pomdp_belief.py selftest`
Regenerate the Codex build after governance/procedure edits	`python build-codex-agents.py`
Rebuild the Cowork plugin package (Cowork = WIP)	`python build-cowork-plugin.py`
Sync skill changes to the user-wide install	`robocopy .claude\skills\aletheia "%USERPROFILE%\.claude\skills\aletheia" /E /XD __pycache__`

Standing rules for changes in this repo

Never hand-edit tunable parameters (sensor reliabilities and thresholds in .claude/skills/aletheia/reference/environment-prior.md). They change only through the sanctioned tuning workflow (I12): autotune.py fit → gates → apply, with a ledger row.
After any change under .claude/skills/aletheia/, run the sync command above — the user-wide install is a deployment copy and does not update itself. Then rebuild the Cowork package if the change should reach Cowork.
SKILL.md stays constant-size. Schemas, parameters, and data belong in reference/ files or runs/; SKILL.md gets pointers only. Its frontmatter description must never contain angle-bracket / XML-like tokens (Cowork's plugin validator rejects them).
Working state is evidence — never delete it. runs/ (belief files = the user's audit trail) and ~/.claude/aletheia-runs/ (telemetry spool, archive, quarantine) are retained per the archive-never-destroy rule in AGENTS.md.
Every user-facing Verdict and outward artifact must pass the leak scan (I1). The test suite enforces this for committed artifacts; run it manually for new ones.
Applied tuning changes get a ledger entry in docs/Aletheia-loop-engg.md (the tuner appends automatically; manual tunes must do the same).
Build the Cowork package only with build-cowork-plugin.py — never a hand-rolled zip (canonical layout and forward-slash entry paths are required by the uploader).

Read the full file on GitHub · 69 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.

2mo ago First seen · 69 lines · 1,099 tokens per session scan A 0bf593139ae1

Subscribe to this mod's changes

Aletheia CLAUDE.md is an instructions file published in the GitHub repository nsankar/Aletheia (5 stars, last pushed 4mo ago), licensed MIT. It adds 1,099 tokens to every session, about $0.0044 per session on Opus 5.5. 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.

Aletheia CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Aletheia CLAUDE.mdnsankar/Aletheia	Instructions file	5	4mo ago	MIT	A	1,099	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

Aletheia: Instructions file for Claude Code