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-decisionsgit 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-decisions)<a href="https://agentmods.dev/skills/felipesauer/mnema/recording-decisions"><img src="https://agentmods.dev/badge/skills/felipesauer/mnema/recording-decisions/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-decisions"><img src="https://agentmods.dev/badge/skills/felipesauer/mnema/recording-decisions.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 | $0.00046 | $0.01006 |
| Opus 5.5 | $0.00018 | $0.00402 |
| Sonnet 5.5 | $0.00009 | $0.00201 |
| Haiku 4.5 | $0.00005 | $0.00101 |
Grade A, and why
recording-decisions 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 6d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recording decisions
A choice settled in this session and not recorded is gone when the session ends: the next session works it out again, or undoes it. mnema is this project's signed, append-only record of those choices, kept with the repository, and the server this plugin connects is the way to write to it.
When it applies
- A choice was settled that someone could later question: a library, an approach, a trade-off.
- An option was turned down, and the reason is not in the code.
- The person told you how something is to be done here, or corrected how you did it.
What to do
- Look first.
governing_ruleswith a path lists what is already recorded for it, andsearchfinds a record by the words written in it. A choice that is already recorded is not recorded again. - Record it when it is settled, not in a batch at the end:
record_decision, with therationaleand, inalternatives, what was turned down and why. - A decision is born
proposed. A person accepts it; it is in force here once accepted, and not before. - Something learnt about this project that its code does not show, and that the next session
would otherwise work out again, goes to
capture_memory. - A rule that governs a path is enforced at the host's editing tools, not at its shell. Writing
to such a path through the shell (
sed -i, a redirect) goes round the rule and is not done: if the rule stands in the way, say so to the person.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago Changed · +3 lines ca8a0d8d808a
- 8d ago Changed · +3 lines a8791de395aa
- 10d ago Changed · +1 lines 2c904129dee6
- 13d ago First seen · 52 lines · 46 tokens per session scan A 61f4facbc29d
recording-decisions is a skill published in the GitHub repository felipesauer/mnema (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 46 tokens to every session and 1,006 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.