Engram is a local or cloud-backed memory system for AI coding agents, provided as a single Go binary with SQLite full-text search and interfaces including a command line, HTTP API, MCP server, and terminal UI. It helps compatible coding agents retain project decisions, bugs, conventions, and other useful context across sessions. The catalogue add-ons configure and operate Engram’s memory workflows.
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 Gentleman-Programming/engram --skill plugin-thingit clone --depth 1 https://github.com/Gentleman-Programming/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/gentleman-programming/engram/plugin-thin)<a href="https://agentmods.dev/skills/gentleman-programming/engram/plugin-thin"><img src="https://agentmods.dev/badge/skills/gentleman-programming/engram/plugin-thin/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/gentleman-programming/engram/plugin-thin"><img src="https://agentmods.dev/badge/skills/gentleman-programming/engram/plugin-thin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.00521 |
| Opus 5.5 | $0.00014 | $0.00208 |
| Sonnet 5.5 | $0.00007 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
engram-plugin-thin 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 7d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use
Use this skill when:
- Editing plugin hooks/scripts/adapters
- Adding passive/active memory capture integrations
- Wiring agent-specific setup behavior
Boundary Rules
- Keep adapters thin: parse input, call API/tool, return.
- Put complex logic in Go core (
store/server/mcp). - Avoid extra runtime dependencies in plugin scripts.
- Reuse a shared contract across all supported agents.
Narrow Pi Exception: Observation-Save Acknowledgement Recovery
plugin/pi native mem_save may resolve only an ambiguous acknowledgement because
the Go server cannot observe that a client lost one. Go remains the sole authority
for the durable ledger, canonical fingerprint, validation, conflicts, tombstones,
retention, and mutation effects.
- Generate one operation UUID before the initial dispatch and freeze the exact redacted payload and both destinations.
- On ambiguity, query only authoritative
GET /observations/save-result. A typed404with codeobservation_save_result_not_foundpermits one exact replay after the cancellable 250 ms backoff. A positive replay receipt succeeds immediately; only an ambiguous replay, including a replay409or410, gets one final GET. - Keep existing total-deadline and caller-cancellation bounds. A lookup confirms
success only with a positive ID and
status: "committed"; a successful initial POST retains legacy positive{id}acknowledgement compatibility. - Initial received HTTP errors remain typed and never replay or self-heal. Caller cancellation is propagated; unresolved write uncertainty remains unknown, never saved.
- This exception grants no other route or tool retry authority, no general retry framework, no local business ledger decision, and no telemetry exemption. Timing telemetry may not log the operation UUID; it grants no broader logging permission or change to existing user-facing unknown-outcome diagnostics that expose it for read-only lookup.
Compatibility Checklist
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.
- 7d ago Changed · +28 lines · +2 tokens per session e478d63f5efb
- 1mo ago First seen · 36 lines · 32 tokens per session scan A 212f1fe18f6a
engram-plugin-thin is a skill published in the GitHub repository Gentleman-Programming/engram (7,360 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 521 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…