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.
Borrowing it
Nothing to install: this file belongs to Gentleman-Programming/engram. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Gentleman-Programming/engram/main/AGENTS.mdgit 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/instructions/gentleman-programming/engram/agents-md)<a href="https://agentmods.dev/instructions/gentleman-programming/engram/agents-md"><img src="https://agentmods.dev/badge/instructions/gentleman-programming/engram/agents-md/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/instructions/gentleman-programming/engram/agents-md"><img src="https://agentmods.dev/badge/instructions/gentleman-programming/engram/agents-md.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 | $0.01042 | $0.01042 |
| Opus 5.5 | $0.00417 | $0.00417 |
| Sonnet 5.5 | $0.00208 | $0.00208 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
engram AGENTS.md 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 11d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engram — Agent Skills Index
Before contributing, read CONTRIBUTING.md for the issue-first workflow.
The contribution policy transition is PRE-CUTOVER / NOT ACTIVE; continue following the active issue-first requirements.
When working on this project, load the relevant skill(s) BEFORE writing any code.
How to Use
- Check the trigger column to find skills that match your current task
- Load the skill by reading the SKILL.md file at the listed path
- Follow ALL patterns and rules from the loaded skill
- Multiple skills can apply simultaneously
Skills
| Skill | Trigger | Path |
|---|---|---|
engram-architecture-guardrails |
Any change that affects system boundaries, ownership, state flow, or cross-package responsibilities. | skills/architecture-guardrails/SKILL.md |
engram-branch-pr |
When creating a pull request, opening a PR, or preparing changes for review. | skills/branch-pr/SKILL.md |
engram-business-rules |
Any change that affects sync behavior, project controls, permissions, or memory semantics. | skills/business-rules/SKILL.md |
engram-commit-hygiene |
Any commit creation, review, or branch cleanup. | skills/commit-hygiene/SKILL.md |
engram-cultural-norms |
Starting substantial work, reviewing changes, or defining team conventions. | skills/cultural-norms/SKILL.md |
engram-dashboard-htmx |
Any change to htmx attributes, partial updates, forms, or server-rendered browser UI. | skills/dashboard-htmx/SKILL.md |
engram-docs-alignment |
Any code or workflow change that affects user or contributor behavior. | skills/docs-alignment/SKILL.md |
engram-issue-creation |
When creating a GitHub issue, reporting a bug, or requesting a feature. | skills/issue-creation/SKILL.md |
engram-memory-protocol |
Decisions, bugfixes, discoveries, preferences, or session closure. | skills/memory-protocol/SKILL.md |
engram-plugin-thin |
Changes in plugin scripts/hooks for Claude, OpenCode, Pi, Gemini, or Codex. | skills/plugin-thin/SKILL.md |
engram-pr-review-deep |
Reviewing any external or internal contribution before merge. | skills/pr-review-deep/SKILL.md |
engram-project-structure |
Creating files, packages, handlers, templates, styles, or tests in this repo. | skills/project-structure/SKILL.md |
engram-server-api |
Any route, handler, payload, or status code modification. | skills/server-api/SKILL.md |
engram-testing-coverage |
When implementing behavior changes in any package. | skills/testing-coverage/SKILL.md |
engram-tui-quality |
Changes in model, update, view, navigation, or rendering. | skills/tui-quality/SKILL.md |
engram-ui-elements |
Adding or changing dashboard UI components or connected browsing flows. | skills/ui-elements/SKILL.md |
engram-visual-language |
Any dashboard styling, typography, spacing, or visual identity change. | skills/visual-language/SKILL.md |
engram-backlog-triage |
Auditing open issues or PRs, triaging the backlog, or reviewing contributor submissions as a maintainer. | skills/backlog-triage/SKILL.md |
gentleman-bubbletea |
When editing Go files in installer/internal/tui/, working on TUI screens, or adding new UI features. | skills/gentleman-bubbletea/SKILL.md |
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.
- 11d ago Changed · +2 lines · +33 tokens per session 383b2b8cbd97
- 28d ago Changed · +2 tokens per session 8eabed5556d7
- 1mo ago Changed · +2 lines · +23 tokens per session 091e7d0aa655
- 2mo ago Changed · -1 lines · -41 tokens per session 5b1d3ffa90a2
- 2mo ago First seen · 36 lines · 1,025 tokens per session scan A 8444fe684151
engram AGENTS.md is an instructions file published in the GitHub repository Gentleman-Programming/engram (7,815 stars, last pushed yesterday), licensed MIT. It adds 1,042 tokens to every session, about $0.0042 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.
engram AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| engram AGENTS.mdGentleman-Programming/engram | Instructions file | 7.8k | yesterday | MIT | A | 1,042 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |