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 instructions/bobaba76/engram/agents-mdgit clone --depth 1 https://github.com/bobaba76/EngramWhat 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 | $0.00736 | $0.00736 |
| Opus 5 | $0.00368 | $0.00368 |
| Sonnet 5 | $0.00147 | $0.00147 |
| Haiku 4.5 | $0.00074 | $0.00074 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
coder MCP - Primary Code Intelligence
This project uses coder MCP as the primary code-intelligence layer for codebase discovery, symbol lookup, dependency tracing, impact review, test discovery, and implementation context.
Prefer coder MCP for this repository. Use other code-intelligence tools only as optional fallbacks or secondary cross-checks when coder MCP cannot answer a question clearly.
Always Do
- Use coder MCP first when you need to locate files, symbols, routes, tests, dependencies, execution context, or likely implementation areas.
- Use
coder_semantic_code_searchorcoder_investigate_codebasewhen exploring unfamiliar features or trying to find the authoritative implementation. - Use
coder_resolve_targetandcoder_unified_contextwhen you need focused symbol-level context (callers, callees, deps, neighborhood in one call). - Before modifying a function, class, method, route handler, shared module, public header, API contract, or embedded firmware boundary, use coder MCP to inspect symbol context, callers/callees, dependencies, or change impact as appropriate.
- Use
coder_find_tests_for_targetbefore or after implementation to identify relevant tests. - Use
coder_detect_changes,coder_change_impact_report, orcoder_post_change_reviewto review changed files, likely affected behavior, and test scope when preparing a commit or handoff. - For C/C++/embedded projects, use
coder_get_dependencies,coder_unified_context, andcoder_detect_changesto inspect header fan-in, call relationships, project/build files, startup/ISR/trap files, and peripheral/init/flash modules. - If coder MCP reports stale, incomplete, or low-confidence results, use normal file search/read tools or another code-intelligence system as a fallback.
Never Do
- NEVER skip reviewing callers, dependencies, or likely test scope for changes to shared or high-risk code.
- NEVER commit or hand off changes without reviewing local change scope using coder MCP or equivalent git diff inspection.
- NEVER ignore low-confidence C/C++ results when compiler/build context is missing. Treat them as useful guidance, then verify with source and build knowledge.
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 First seen · 46 lines · 736 tokens per session scan A afdceb183bf7
Engram AGENTS.md is an instructions file published in the GitHub repository bobaba76/Engram (5 stars, last pushed 15d ago), licensed MIT. It adds 736 tokens to every session, about $0.0037 per session on Opus 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 2026-08-31.
Other instructions, from other repositories
Financial-API AGENTS.md
Instructions for HiThink-Tech/Financial-API, covering agents.md, 必读顺序, monorepo 边界, 选择接入方式 and api key.
repobrain copilot-instructions.md
Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.
repobrain AGENTS.md
AGENTS.md instructions for study8677/repobrain: Beautiful is better than ugly. Explicit is better than implicit. Simple is better than complex. Complex is better than complicated. Flat is better than nested. Sparse is better than dense. Readability counts. Special cases aren't special enough to break the rules.…
sverklo CLAUDE.md
Instructions for sverklo/sverklo, covering sverklo development, using sverklo tools, project structure and build & test.
codesage AGENTS.md
Instructions for iliaal/codesage, covering codesage, build, sanity check before pushing, crate map and search pipeline.
mcpls rust-config.instructions.md
Instructions for bug-ops/mcpls, covering type safety and idiomatic config and msrv and dependencies.