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/rodspeed/epistemic-memory/mirrornpx skills add rodspeed/epistemic-memory --skill mirrorgit clone --depth 1 https://github.com/rodspeed/epistemic-memoryWrote 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/rodspeed/epistemic-memory/mirror)<a href="https://agentmods.dev/skills/rodspeed/epistemic-memory/mirror"><img src="https://agentmods.dev/badge/skills/rodspeed/epistemic-memory/mirror.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 | $0.00000 | $0.02233 |
| Opus 5 | $0.00000 | $0.01117 |
| Sonnet 5 | $0.00000 | $0.00447 |
| Haiku 4.5 | $0.00000 | $0.00223 |
Grade A, and why
mirror 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mirror — Portrait, Audit & Interview Skill
Surface what the AI knows about the user — as a person, not as a dataset.
Modes:
/mirror— prose portrait: "here's who I think you are," organized by theme/mirror audit— epistemological dashboard: confidence distributions, dormancy decay, drift analysis, tensions/mirror gut-check— interactive belief validation/mirror interview— structured conversation to see the user more fully
Instructions
Step 1: Load Profile Data
Read all user profile files from your project's memory directory:
user/— all.mdprofile documents (beliefs about the user)user/tensions.md— tensions loguser/session-counter.json— session count and last review dateuser/epistemic-protocol.md— dormancy decay parameters and protocol rules
Step 2: Parse Beliefs (silent)
Extract every belief with its metadata. Apply dormancy decay silently using the formula and rates from epistemic-protocol.md. This informs what you write but doesn't appear in the portrait output.
Dormancy decay formula: effective_conf = stored_conf × e^(-λ × days_since_confirmed), floor at 0.20.
- stable: λ ≈ 0.001, durable: λ ≈ 0.005, situational: λ ≈ 0.015, unknown: λ ≈ 0.010
- If
confirmedis—, usefirstdate instead
Portrait Mode (/mirror)
Write a character study of the user. Not a report — a portrait. The reader should finish it feeling like they've met someone real.
Structure
1. The Person
Open with a short paragraph that captures the essence — who this person is in a few sentences. Not a bio. A sketch that a close friend would recognize.
2. Themes
Organize what you know into 4-6 thematic sections. Let the profile's natural clusters guide the themes — don't force categories. Examples of what might emerge:
- How they think
- Where they come from
- What they make
- How they work
- What they want
- What they carry
For each theme, write 2-4 sentences of prose. Draw from the beliefs but write about the person, not the beliefs. Where something is uncertain or only glimpsed, say so naturally — "I've seen hints of X but don't know it well" rather than citing a confidence score.
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 · 201 lines · 0 tokens per session scan A 55f749c5578d
mirror is a skill published in the GitHub repository rodspeed/epistemic-memory (20 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,233 tokens. 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
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
mem-setup
This skill should be used when the user asks to "set up claude-mem", "pair claude-mem", "connect cmem", "add my cmem key", "set up cloud sync in Cowork", or provides cmem.ai Connect values (sync token, user id, SyncHub URL) for this plugin. Configures the claude-mem-cowork plugin credentials.
cognee-cli
Use when the user wants to drive cognee from the terminal with cognee-cli — remember/recall/forget/improve memory commands, managing datasets and config, or database migrations.
cognee-install
Use when the user wants to install cognee and run their first remember → recall flow with the Python SDK — fresh setup, virtual env, extras selection, or a minimal working example.
cognee-server
Use when the user wants to run the cognee API server (and optional UI) on their own machine — starting it, checking it's healthy, connecting the SDK or other clients to it, and choosing the right auth posture.