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 techtheist/engram --skill normalgit clone --depth 1 https://github.com/techtheist/engramWrote 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/techtheist/engram/normal)<a href="https://agentmods.dev/skills/techtheist/engram/normal"><img src="https://agentmods.dev/badge/skills/techtheist/engram/normal/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/techtheist/engram/normal"><img src="https://agentmods.dev/badge/skills/techtheist/engram/normal.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 | $0.00072 | $0.02874 |
| Opus 5.5 | $0.00029 | $0.01150 |
| Sonnet 5.5 | $0.00014 | $0.00575 |
| Haiku 4.5 | $0.00007 | $0.00287 |
Grade A, and why
engram 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.
This is a copy
92% identical to engram — 30 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engram — project memory (Normal)
Engram is a local, user-owned graph of why this project is the way it is: decisions and their reasons, gotchas, problems and their fixes, conventions. Not code structure — the code holds that. The user sees every node in the pane, so quality and honest edges matter more than volume: a noisy graph stops being trusted, and an untrusted graph stops being read.
Normal: balanced capture. Save what a future session would genuinely want to know; skip noise. Don't mirror Claude Code's own memory (CLAUDE.md, auto-memory): Engram holds project reasoning, not user preferences, workflow or code structure.
Recall
- Session start: read the brief. If the session opened with an injected "# Engram brief", that IS it; otherwise call
briefonce. Its first line names the graph — if that is not this workspace, callbrief(project: "<workspace absolute path>"). - Before any non-trivial decision,
search. Read theconfidenceverdict (strongact /weakverify first /nonesay the graph is silent) and each hit'sstanding(contestedandtombstoneare said out loud;superseded→ read the replacement). If a Decision or Caution covers what you're about to do, follow it or raise the contradiction with the user before acting. - On
weak/none, reformulate before concluding absence: name the thing (entity-first), use the words a note would use, or scope in time (after: "last week",during_version). Pass time expressions as written; the daemon resolves them. - Start
detail: "compact"when scanning;fullonly for hits you'll act on.get_node/traversepull the reasoning around a hit;timelinewalks a supersession chain;auditshows who changed what;list_openis the worklist;list_nodesis the lossless read for reviews and exports. - "Why is it like this?" → search, follow
because/answersedges andtimeline, retell as a short dated narrative. - Session history (if the user turned recording on): a weak verdict may carry a
historysection — leads, not knowledge.expand_history(session, turn)before relying on one; capture what matters as a proper note.list_sessionsanswers "what was I doing last Tuesday".
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 Changed · +13 lines c4b640bf0df8
- 6d ago Changed · -118 lines 35ac71135f74
- 18d ago Changed fc1f878663a7
- 22d ago Changed · +1 lines 192a8342594f
- 28d ago Changed · +4 lines 7ba711c942d7
- 1mo ago Changed · +1 lines 92084ebad1de
- 1mo ago First seen · 193 lines · 72 tokens per session scan A e4e4a25cee3e
engram is a skill published in the GitHub repository techtheist/engram (32 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 2,874 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 92% identical to engram, differing in 30 lines, and is treated as a copy.
Other skills, from other repositories
memory-protocol
A shared set of rules for using a persistent memory service across coding-agent sessions.
memory
Activate this skill when starting a new session, beginning a new task, saving knowledge, recalling past decisions, or after completing significant work. Also activate on errors to log them for pattern analysis. Relevant when the user asks about memory, past context, lessons learned, decisions history, project…
session-recap
Document Claude Code sessions by extracting knowledge into cross-referenced documentation. Triggers on "recap the session", "summarize the work", or after significant code changes.
garden-tending
Tend the knowledge garden — diagnose vault health, condense project memos into project.md overviews, create/merge cross-project topics, fix broken links, archive superseded notes, extend trails. Trigger on "tend the garden", "condense", "update project overview", "check vault health", "where are we with X?", "what…
knowledge-bank-lookup
Delegates knowledge bank lookups to Explore subagents with reflections-first strategy that learns from past mistakes. Checks /reflections/ directory before documentation to extract documented failures to avoid and proven approaches to apply. Automatically triggers when user mentions services ([project-a], [project-b]…
kb-ingest
Ingest external sources into the knowledge bank through interactive study or quick filing. Two modes — Quick (summarize → file) and Study (theme-by-theme deep dive with online research and personal notes → multi-layer KB output → optional blog/slack synthesis). Triggers on "ingest this", "study this article", "add to…