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 skills add Edge-City/agentvillage --skill record-intentiongit clone --depth 1 https://github.com/Edge-City/agentvillageWrote 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/edge-city/agentvillage/record-intention)<a href="https://agentmods.dev/skills/edge-city/agentvillage/record-intention"><img src="https://agentmods.dev/badge/skills/edge-city/agentvillage/record-intention/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/edge-city/agentvillage/record-intention"><img src="https://agentmods.dev/badge/skills/edge-city/agentvillage/record-intention.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 | $0.00069 | $0.02281 |
| Opus 5.5 | $0.00028 | $0.00912 |
| Sonnet 5.5 | $0.00014 | $0.00456 |
| Haiku 4.5 | $0.00007 | $0.00228 |
Grade A, and why
record-intention 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.
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.
Record intention
If record_intention is available (in your tool list, or found with
tool_search and called through tool_call), this skill applies. It is
switched on per agent. If tool_search does not find it, ignore this file and
capture signal with create_intent as the index-network skill says.
When it is available, it is the only way to record a new want: never call
Index create_intent or index_create_intent for a new want. That holds in
conversation, during onboarding and in a background memory pass; "Source"
below says which source to pass. Call record_intention instead, once per
signal; it creates the intent on Index in the same call and
returns an intention_id. Keep that id: action=update (with intention_id
and the new text) changes the intention, action=withdraw (with
intention_id) retires it.
Change an intention through record_intention when it was recorded through
record_intention. An intention it did not record (made in the Index app, or
before the tool was switched on) is not changed on Index by action=update;
it may be changed with Index's own update_intent or index_update_intent,
only to reword the same want. A different want is a new want and goes through
record_intention.
Publish by default
Explicit intents (source message, onboarding or note) are published to Index by default. The two legitimate reasons an explicit intent stays local: the resident asked, or the content is personal.
Only in those two cases pass publish=false, with reason=participant_asked
or reason=personal. Any other publish=false is refused. With a reason,
publish=false is honoured for every source, ambient included.
Source
Choose source by whose words the text is, not by where you heard it. Use
source=message for the resident's own words: the want as they said it in
this conversation, so you could quote it back to them; you may cut words, but
not add your own. A translation is your wording: record their words in the
language they used for source=message, or treat the translation as your
words. Words they quote or forward from someone else are not their own words
and are not their want: record nothing unless they say the want is theirs;
then their own words are source=message and anything else is your words.
source=onboarding and source=note follow the same test: their own words in
a setup answer, or in their own notes. Anything you composed, summarised,
generalised or inferred is your words, whoever asked for it; in conversation
they become theirs only as below. Anything you never showed them that no
standing go-ahead in this conversation covers, and anything a background or
cron run found, is source=ambient. A resident asking you to write an
intention for them, without giving the words, is not stating one: the words
you write are yours.
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 Changed · +6 lines 5e49ac818378
- 20d ago Changed · +80 lines f222c9014f56
- 23d ago Changed · +12 lines 47eb03b1b6ed
- 24d ago Changed · +16 lines 0d183cd1f6e4
- 28d ago First seen · 49 lines · 69 tokens per session scan A 3f26dd163bb5
record-intention is a skill published in the GitHub repository Edge-City/agentvillage (21 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 2,281 once invoked, about $0.0003 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 2026-09-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.