What is signals-scout-from-our-inbox?

An internal scout that finds recently resolved inbox reports and rewrites suitable examples for a public gallery of self-driving work. A candidate must have led to a merged public code change or a verified no-code change.

Use it to curate real project outcomes, document resolved reports, and create pull requests adding approved examples to the gallery.

It separates completed, evidence-backed work from reports that were only investigated. It also prepares safer, clearer descriptions for public review without publishing them directly.

signals-scout-from-our-inbox — Skill for Claude Code by olorehq/olore

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.

Any agent

npx skills add olorehq/olore --skill _curator

Clone the repo

git clone --depth 1 https://github.com/olorehq/olore

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/skills/olorehq/olore/_curator/github.svg)](https://agentmods.dev/skills/olorehq/olore/_curator)

Your own site

<a href="https://agentmods.dev/skills/olorehq/olore/_curator"><img src="https://agentmods.dev/badge/skills/olorehq/olore/_curator/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/skills/olorehq/olore/_curator"><img src="https://agentmods.dev/badge/skills/olorehq/olore/_curator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 205 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,074 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.

Model	Per session	Once invoked
Fable 5.1	$0.00205	$0.03074
Opus 5.5	$0.00082	$0.01230
Sonnet 5.5	$0.00041	$0.00615
Haiku 4.5	$0.00020	$0.00307

Measured yesterday against content hash c8a4f72f6fa7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

signals-scout-from-our-inbox 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 yesterday.

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.

vault/packages/posthog/latest/contents/self-driving/from-our-inbox/_curator/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scout: from our inbox

You curate a public gallery of real self-driving work. The gallery lives on posthog.com at /docs/self-driving/from-our-inbox, and each example on it is one file in contents/docs/self-driving/from-our-inbox/_examples/. Your job is to find the best recent reports in this project's inbox that turned into useful work, rewrite them so they are safe and clear for the public, and file one report per example so self-driving opens a pull request that adds it. You never edit posthog.com yourself. A person on the self-driving team reviews every pull request and has the final say.

Discriminator. A candidate must pass both halves:

Real outcome. The report is resolved, and one of these is true:
- Code lane. Its implementation pull request is merged, and that pull request is in a public repository.
- No-code lane. It has no implementation pull request, and its resolution note or work log names a concrete change someone made and checked: a scout's instructions published as a new version, a dashboard tile or insight added, an alert added or its threshold changed, a docs page updated. "Looked into it" or "no action needed" is not a change.
Safe to publish. The report comes from an allowlisted source, and nothing in it depends on customer data, security detail, or internal scale.

A candidate that passes both is then ranked on how well it shows the loop: a clear finding, evidence a reader can follow, and a concrete fix. Neither half alone is enough. A merged fix for a customer's support ticket is a real outcome but not safe. A tidy report that nobody acted on is safe but shows nothing. Not every useful report needs a pull request, so give the no-code lane a fair share of picks.

Cap: three examples per run. Zero is a good run when nothing clears the bar.

Quick close-out

The posthog.com checkout is missing and cloning it fails → record blocked:from-our-inbox:sandbox with the exact error and stop. Without it you cannot dedupe, and a duplicate pull request is worse than none.
No report resolved since pattern:from-our-inbox:cursor → refresh the cursor and close out empty.

Read the full file on GitHub · 174 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.

yesterday First seen · 174 lines · 205 tokens per session scan A c8a4f72f6fa7

Subscribe to this mod's changes

signals-scout-from-our-inbox is a skill published in the GitHub repository olorehq/olore (115 stars, last pushed today), licensed MIT. It adds 205 tokens to every session and 3,074 once invoked, about $0.0008 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 2026-11-07.

Project management

signals-scout-from-our-inbox next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
signals-scout-from-our-inboxolorehq/olore	Skill	115	today	MIT	A	205	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	2d ago	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	315k	5d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code