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 dragthelake/ambient-context --skill ambient-context-tune-rulesgit clone --depth 1 https://github.com/dragthelake/ambient-contextWrote 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/dragthelake/ambient-context/ambient-context-tune-rules)<a href="https://agentmods.dev/skills/dragthelake/ambient-context/ambient-context-tune-rules"><img src="https://agentmods.dev/badge/skills/dragthelake/ambient-context/ambient-context-tune-rules/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/dragthelake/ambient-context/ambient-context-tune-rules"><img src="https://agentmods.dev/badge/skills/dragthelake/ambient-context/ambient-context-tune-rules.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 | $0.00058 | $0.00466 |
| Opus 5 | $0.00029 | $0.00233 |
| Sonnet 5 | $0.00012 | $0.00093 |
| Haiku 4.5 | $0.00006 | $0.00047 |
Grade A, and why
ambient-context-tune-rules 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 2d 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.
What it actually says
Tune rules
Follow the ambient-context skill's conventions. This skill writes, so the app must be open; capture_status returning not_running means stop and say so.
A rule has a target (an app, a website or a window title) and an action: exclude (never keep), headings_only (keep the block heading, drop the body), full (keep everything, overriding a broader rule) or route_messages (send the block to the messages file). Every rule change is logged in the ledger with this client's name.
Steps
list_rulesfirst. Read the built-in rules as well as the user's; many requests are already covered, and built-ins cannot be weakened.- Find the evidence.
search_recordfor the app, site or phrase the user named, orread_dayon the window they mean. Quote the heading, not the body. - Draft the smallest change that does what they asked: one rule where one will do. Prefer editing an existing rule over adding a near-duplicate.
- Show the change as a diff: the rule before (or "none") and the rule after, with one line on what it will stop or move from the next snapshot on. Say that text already recorded is not changed.
- Wait for a yes. Then apply with
add_rule,update_ruleorremove_rule, one call per rule. - Confirm in one line what was applied and that it is in today's ledger.
Do not
- Apply anything before the user agrees, even a removal they asked for.
- Add a rule from a single occurrence without saying it was one occurrence.
- Change the prompt or config here; that is a different request.
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.
- 2d ago First seen · 29 lines · 58 tokens per session scan A 41bc563d5ac0
ambient-context-tune-rules is a skill published in the GitHub repository dragthelake/ambient-context (165 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 466 once invoked, about $0.0003 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 2026-09-07.
Other skills, from other repositories
project-wiki
A system for creating and maintaining a project wiki: a set of organized documents that explain a software project's plans, rules, references, and progress.
mindos-zh
A local knowledge-base assistant for storing and finding decisions, meeting notes, procedures, troubleshooting lessons, and preferences across conversations and coding agents. It works only with the MindOS knowledge base.
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…
mindos-max
MindOS: local knowledge assistant & global memory layer. Keeps decisions, notes, SOPs, debugging lessons, architecture choices, research findings, preferences, conversation summaries for all connected agents. PROACTIVE: (1) search MindOS first for past context, (2) offer to save after valuable work, (3) persist key…
mindos
Operate a MindOS knowledge base: update notes, search, organize files, execute SOPs/workflows, retrospective, append CSV, cross-agent handoff, route unstructured input to the right files, distill experience, sync related docs. Use when the task targets files inside the user's MindOS KB (mindRoot). NOT for editing app…
plugin-core-builtin-migration
A repeatable process for turning an optional MindOS renderer plugin into a built-in, always-available part of the application. It also covers moving old entry points while keeping existing data usable.