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.
npx agentmods add skills/elbwalker/walkeros/walkeros-understanding-storesnpx skills add elbwalker/walkerOS --skill walkeros-understanding-storesgit clone --depth 1 https://github.com/elbwalker/walkerOSWrote 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/elbwalker/walkeros/walkeros-understanding-stores)<a href="https://agentmods.dev/skills/elbwalker/walkeros/walkeros-understanding-stores"><img src="https://agentmods.dev/badge/skills/elbwalker/walkeros/walkeros-understanding-stores.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.04447 |
| Opus 5 | $0.00023 | $0.02224 |
| Sonnet 5 | $0.00009 | $0.00889 |
| Haiku 4.5 | $0.00005 | $0.00445 |
Grade A, and why
walkeros-understanding-stores 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 5d 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 — 509 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Understanding walkerOS Stores
Overview
Stores provide key-value storage that other components (sources, transformers, destinations) consume via environment injection. They are the 4th component type in Flow.Json alongside sources, transformers, and destinations.
Core principle: Stores are passive infrastructure. They don't process events or participate in chains — they provide state that other components read and write.
Store interface
See packages/core/src/types/store.ts for the canonical interface.
Instance
| Property | Type | Purpose | Required |
|---|---|---|---|
type |
string |
Store type identifier | Required |
config |
Store.Config |
Settings and env | Required |
get |
(key) => StoreValue | undefined |
Read a value | Required |
set |
(key, value, ttl?) => void |
Write a value (optional TTL) | Required |
delete |
(key) => void |
Remove a value | Required |
destroy |
DestroyFn |
Cleanup on shutdown | Optional |
All methods can be sync or async (return Promise).
Value type and file mode
Stores hold one canonical value type: structured data (StoreValue), with
binary (Uint8Array) as a first-class leaf. StoreValue is
string | number | boolean | null | Uint8Array | StoreValue[] | { [key: string]: StoreValue }
(undefined is reserved as the "miss" sentinel and is never a stored value). A
shared core codec (serializeStoreValue / deserializeStoreValue) round-trips
that value to and from each backing.
Store.Config.file?: boolean (default false) picks the mode, decided once at
init:
- Structured (default): values are
StoreValuedata, serialized by the shared codec. - File (
file: true): a byte-native backend (fs, S3, GCS) persists raw bytes byte-exact.set()accepts aUint8Arrayorstringand stores it untouched;get()hands the exact bytes back. Use for serving assets such as walker.js. The Sheets store is structured-only and rejectsfile: trueat init.
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.
- 5d ago First seen · 509 lines · 45 tokens per session scan A af304932b2a4
walkeros-understanding-stores is a skill published in the GitHub repository elbwalker/walkerOS (343 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 4,447 once invoked, about $0.0002 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.
Other skills, from other repositories
task-management
Task management CLI for tracking and managing feature subtasks with status, dependencies, and validation.
meter-off
Disable CocoMeter token tracking. Finalizes the current session record and appends to history. Does not delete history — just stops active tracking.
meter-on
Enable CocoMeter token and credit tracking for this session. Creates tracking state in .cocoplus/meter/ and activates per-tool token capture via post-tool-use hook.
solr-semantic-search
To build Solr phrase-tagging semantic search: concept tagging, taxonomy, graph paths.
content-enrich
内容加工:给任意采集产物(转录稿 / 文章 / 笔记)自动补「摘要 + 要点 + 标签 + 价值判断」, 写进 frontmatter 并在正文顶部插入摘要块。是「加工层」通用能力,惠及仓库所有采集 skill。.
issue-progress-tracking
GitHub issue workflow ceremony using gh CLI — labels issues as in-progress, creates feature branches (issue/N-description), commits with issue references, posts progress comments, and links PRs with Closes #N. Keeps issues in sync with development work. Use when starting work on an issue, tracking progress, or…