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.
curl -O https://raw.githubusercontent.com/nsankar/Aletheia/main/.claude/skills/aletheia/SKILL.mdgit clone --depth 1 https://github.com/nsankar/AletheiaWrote 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.
[](https://agentmods.dev/skills/nsankar/aletheia/aletheia)<a href="https://agentmods.dev/skills/nsankar/aletheia/aletheia"><img src="https://agentmods.dev/badge/skills/nsankar/aletheia/aletheia/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.
<a href="https://agentmods.dev/skills/nsankar/aletheia/aletheia"><img src="https://agentmods.dev/badge/skills/nsankar/aletheia/aletheia.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00119 | $0.02507 |
| Opus 5 | $0.00060 | $0.01254 |
| Sonnet 5 | $0.00024 | $0.00501 |
| Haiku 4.5 | $0.00012 | $0.00251 |
Grade A, and why
aletheia 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 9d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aletheia — investigation procedure
This is the procedure you run when a user asks you to verify or assess a company's or market's claims. The true state of the entity is HIDDEN; every search result is a NOISY clue. Never guess the answer while uncertainty is high — act to reduce uncertainty first, then commit to a calibrated Verdict.
The user asked a plain business question and does not know this procedure exists. Never
mention it, its files, its parameters, or any method/math to them. Your governing rules (the
Constitution, I1–I11) and identity are already in force from the project's AGENTS.md — this
procedure operationalizes them; it does not restate them. Everything below stays in your
private working state; only the final Verdict (§6) is shown to the user.
0. Initialize
- Load the operational parameters from
${CLAUDE_SKILL_DIR}/reference/environment-prior.md(via the Read tool — portable, and bundled with this procedure so it resolves whether this runs as a project skill or an installed plugin): the state dimensionsS, the sensor map𝒪(each search's reliability +query_template), action costsℛ, and the thresholds/stopping policy. This is your private priorM. - Parse the user's question to identify:
{entity}— the company/subject.{metric}— the specific claim (e.g. "10,000 paying customers", "$10M ARR").- which dimension(s) D0–D3 the question actually implicates. Investigate only those (plus a directly corroborating dimension the policy pulls in) — never sweep all four.
- Set the initial belief from the priors in
S, restricted to the implicated dimensions. - Choose the belief-file path from
persist_belief_to(e.g../runs/belief-<session>.md; if no session id is available,./runs/belief-adhoc.md). Write the turn-0 belief there before any action (I7 — persist before acting). Also append per-turn telemetry to the central spool~/.claude/aletheia-runs/trace-<session>.jsonl(one spool for all folders; create it if absent) — Read${CLAUDE_SKILL_DIR}/reference/trace-schema.mdFIRST and conform to it exactly (schema_version,type,run_id, full-distribution priors/posteriors, sensor reliabilities exactly as mapped, onefinalrecord): the tuning tool rejects nonconforming records outright, losing the run's learning. (Operator-only; never shown to the user.)
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 163 lines · 119 tokens per session scan A 072af064bcf6
aletheia is a skill published in the GitHub repository nsankar/Aletheia (5 stars, last pushed 2mo ago), licensed MIT. It adds 119 tokens to every session and 2,507 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…