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 vasilyu1983/AI-Agents-public --skill agents-memorygit clone --depth 1 https://github.com/vasilyu1983/AI-Agents-publicWrote 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/vasilyu1983/ai-agents-public/agents-memory)<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/agents-memory"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/agents-memory/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/vasilyu1983/ai-agents-public/agents-memory"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/agents-memory.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 | $0.00043 | $0.05476 |
| Opus 5 | $0.00022 | $0.02738 |
| Sonnet 5 | $0.00009 | $0.01095 |
| Haiku 4.5 | $0.00004 | $0.00548 |
Grade D, and why
agents-memory scanned grade D with 2 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 9d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
- `<!-- audit-ignore: ./gradlew, res/values/strings.xml -->` — whitelist intentional non-existent paths (DON'T-do-this examples, future tooling). Glob patterns supported. Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| Codex runtime permissions | `~/.codex/config.toml`, trusted `.codex/config.toml`, permission profiles, `.rules` | Configure sandbox boundaries, approval policy/reviewer, and executable command policy | How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Memory for Claude Code + Codex
Configure project memory so Claude Code and Codex get stable, scoped instructions across sessions without bloating every prompt. For shared teams, keep the portable project rules in AGENTS.md, mirror that into CLAUDE.md when needed, and keep tool-specific behavior in the tool's native layer.
Treat repo memory as a living exception file. If an agent can reliably infer something by reading the code, config, or README, keep it out of the always-loaded layer. Put only the durable, non-inferable guidance here.
Quick Reference
| Layer | Typical Location | Purpose |
|---|---|---|
| Shared project memory | ./AGENTS.md |
Portable repo instructions for Codex and other AGENTS.md-aware tools |
| Claude project memory | ./CLAUDE.md |
Claude Code project instructions; often a symlink or mirror of AGENTS.md |
| Claude scoped rules | ./.claude/rules/*.md |
Modular Claude-only rules, optionally path-scoped |
| Codex personal instructions | ~/.codex/AGENTS.md |
Personal behavioral guidance across repositories |
| Codex directory override | ./AGENTS.override.md |
Higher-precedence guidance for one directory; it may be local or checked in |
| Codex runtime permissions | ~/.codex/config.toml, trusted .codex/config.toml, permission profiles, .rules |
Configure sandbox boundaries, approval policy/reviewer, and executable command policy |
| Codex auto-memory | ~/.codex/memories/ (opt-in via [features] memories = true) |
Machine-local accumulated recall; off by default; keep must-always rules in AGENTS.md, not here |
| Claude auto memory | ~/.claude/projects/<project>/memory/ — MEMORY.md index + topic files |
Machine-local, accumulated notes; first 200 lines / 25 KB of MEMORY.md load each session; topic files load on demand |
| Instruction budget | ~100–150 usable lines across all loaded CLAUDE.md tiers | Community-derived heuristic (not an official Anthropic figure): compliance drops past ~150–200 discrete instructions, of which the system prompt already spends ~50; budget is a shared pool across all tiers |
| Layered memory model | references/memory-patterns.md |
Keep the hot memory small; push history and reusable procedures into the right layers |
What ships with it
30 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 359 B
- data/sources.json 20 KB
- learnings.consolidated.md 589 B
- learnings.md 717 B
- references/claude-managed-agents-memory.md 4.3 KB
- references/claude-md-fragments.md 12 KB
- references/claude-md-instruction-budget.md 5.8 KB
- references/coding-behavior-completeness.md 10 KB
- references/coding-behavior.md 17 KB
- references/cross-doc-audit.md 9.4 KB
- references/harness-audit.md 3.9 KB
- references/large-codebase-strategy.md 11 KB
- references/loading-and-layers.md 6.4 KB
- references/memory-architecture-ceilings.md 11 KB
- references/memory-discipline.md 4.5 KB
- references/memory-examples.md 41 KB
- references/memory-patterns.md 33 KB
- references/nested-feature-memory-examples.md 6.4 KB
- references/opus-4-7-memory-migration.md 8.5 KB
- references/platform-and-scale.md 3.4 KB
- references/portfolio-audit-runbook.md 6.8 KB
- references/real-world-advanced.md 10 KB
- references/structure-patterns.md 2.6 KB
- references/traps-and-antipatterns.md 9.6 KB
- references/typical-scenarios.md 11 KB
- references/zero-to-working-recipe.md 5.4 KB
- scripts/audit_portfolio.sh 3.8 KB runs code
- scripts/audit_repo.sh 9.8 KB runs code
- scripts/compare_blocks.sh 4.9 KB runs code
- scripts/lint_claude_memory.sh 3.3 KB runs code
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.
- 9d ago First seen · 303 lines · 43 tokens per session scan D 9c58c9ee4c69
agents-memory is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (87 stars, last pushed 7d ago), licensed MIT. It adds 43 tokens to every session and 5,476 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (hidden instructions, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
continuum-memory
Configure and use Continuum's two-tier memory system — mem0+Qdrant/Milvus for long-term facts, Redis for short-term sessions, with multi-tenant scopes (USER / AGENT / SHARED / RUN / CONVERSATION). Invoke when the user asks about "remember", "user preferences", "long-term memory", "vector search over memories"…
evolve
Use this skill when extracting session patterns into reusable learnings. Three modes: analyze (extract from session history), review (edit/manage existing learnings), list (display active learnings). Manages .orchestrator/metrics/learnings.jsonl.
memory-cleanup
Use this skill when performing manual memory consolidation (Dream-equivalent). Reviews, consolidates, and prunes memory files under /.claude/projects//memory/. Run after major refactors, every 5+ sessions, or when memory quality degrades (broken links, stale references, contradictions, MEMORY.md > 200 lines). Invoke…
session-handoff
Context transfer between AI sessions. Trigger when the user wants to save the context, resume a task, or hand off the work to another session.
memory-types-team-stores
Use when configuring shared team memory stores and knowledge graphs.
memory-types
Use when managing persistent project memory, facts, and developer context.