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 felipesauer/mnema --skill recording-rulingsgit clone --depth 1 https://github.com/felipesauer/mnemaWrote 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/felipesauer/mnema/recording-rulings)<a href="https://agentmods.dev/skills/felipesauer/mnema/recording-rulings"><img src="https://agentmods.dev/badge/skills/felipesauer/mnema/recording-rulings/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/felipesauer/mnema/recording-rulings"><img src="https://agentmods.dev/badge/skills/felipesauer/mnema/recording-rulings.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 | $0.00038 | $0.00575 |
| Opus 5.5 | $0.00015 | $0.00230 |
| Sonnet 5.5 | $0.00008 | $0.00115 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
recording-rulings 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 13d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recording rulings
Some workflows have the agent decide and go on instead of stopping to ask, and keep what it decided in a ledger beside the work: a line per ruling, with what was ruled, why, and what it costs if it is wrong. Where that ledger is thrown away when the work ends, the calls go with it. Recorded in mnema, they are kept with the repository, signed, and a person can accept or reject each one later.
This skill leaves the workflow as it is. The ledger stays where the workflow keeps it, and each ruling is also recorded.
What a ruling becomes
A ruling is a decision made without waiting for an answer, which is the state a decision is born
in here: proposed, awaiting a judgement. Nothing about it is in force until a person accepts it.
| In the ledger | In the record |
|---|---|
| What was ruled | the title of a record_decision |
| Why | its rationale |
| What it costs if it is wrong | the last line of the rationale, in the same words the ledger used |
| The option it was chosen over | alternatives, with why it was turned down |
Record it when the ruling is made, beside the ledger line, and not in a batch at the end.
What the rest of the ledger becomes
- A minor the work left for later, found in review: a
record_observationabout the record it concerns, by its id; with no record to attach it to,capture_memory. - The state of each step of the plan stays in the workflow's own file. This skill is only about the calls.
A ruling that is already recorded is not recorded again: search finds a record by the words
written in it.
The thoughts that come before a choice goes unrecorded, and what the project measured against each,
are the table in recording-decisions; a ruling is a settled choice like any other, so that table
applies to it. The tools are named the same in every host, and its references/tools-by-host.md
says what each host calls them.
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.
- 13d ago First seen · 51 lines · 38 tokens per session scan A 07822596e67f
recording-rulings is a skill published in the GitHub repository felipesauer/mnema (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 38 tokens to every session and 575 once invoked, about $0.0002 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 2026-10-03.
Other skills, from other repositories
kiro-steering-custom
Create custom steering documents for specialized project contexts.
memory-import
Bulk-import an external knowledge base into Prismer memory via the three-layer import pipeline (07 §3.1). Use when the user asks to import/migrate documents, a knowledge base, or notes into workspace memory. Layer 1 lands raw documents (zero LLM, instantly searchable); Layer 2 is YOUR distillation work — you read the…
prismer-obsidian
Read, search, create, and edit notes in the Obsidian vault.
identity-snapshot
Generate a living profile of the user's working patterns, decision tendencies and quality preferences from their Dex data. Use when the user says 'what are my patterns', 'how do I work', or during week-review. Also use proactively when the model (older than 7 days) is stale. Not for planning a week; use week-plan.
init
Install or update OwnMem in the current repository. Use when the user asks to set up OwnMem, add local project memory for coding agents, or refresh an existing OwnMem installation after a version bump.
memorix-sessions
Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.