agentic-stack is a portable layer of agent memory, skills, and protocols stored in a .agent/ folder that can be used across multiple coding-agent tools. It is for people who switch between agent harnesses while keeping shared knowledge and monitoring data. The catalogue entries provide skills and rules for this shared agent layer.
Borrowing it
Nothing to install: this file belongs to codejunkie99/agentic-stack. 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/codejunkie99/agentic-stack/master/.agent/skills/memory-manager/SKILL.mdgit clone --depth 1 https://github.com/codejunkie99/agentic-stackWrote 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/codejunkie99/agentic-stack/memory-manager)<a href="https://agentmods.dev/skills/codejunkie99/agentic-stack/memory-manager"><img src="https://agentmods.dev/badge/skills/codejunkie99/agentic-stack/memory-manager/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/codejunkie99/agentic-stack/memory-manager"><img src="https://agentmods.dev/badge/skills/codejunkie99/agentic-stack/memory-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 47 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00002 | $0.00757 |
| Opus 5.5 | $0.00001 | $0.00303 |
| Sonnet 5.5 | $0.00000 | $0.00151 |
| Haiku 4.5 | $0.00000 | $0.00076 |
Grade A, and why
memory-manager 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 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.
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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Manager — the skill that reads the filing cabinet
After every major task or failure, call tools/memory_reflect.py to log what
happened. Before important decisions, read the top entries from
memory/semantic/LESSONS.md and memory/semantic/DECISIONS.md.
When to trigger full consolidation
- On explicit
reflecttrigger from the user. - When the context window is getting full.
- When episodic memory exceeds ~500 entries.
Consolidation steps
- Load top-5 episodic entries by salience score.
- Detect recurring patterns across the last 100 entries.
- For patterns appearing ≥3 times, promote to
memory/semantic/LESSONS.md. - Flag any skill with ≥3 failures in 14 days for rewrite (see
on_failure.py). - Archive resolved working context to
memory/episodic/snapshots/. - Commit via git so history is preserved:
git log memory/is the agent's autobiography.
Searching memory by keyword
When you need to find a specific memory by topic or keyword (not just the top-salience entries), use the FTS5 search tool:
python3 .agent/memory/memory_search.py <query>
This indexes all .md and .jsonl files under .agent/memory/ and returns
ranked results with context snippets. Falls back to grep if FTS5 is not
available. The index auto-rebuilds when files change.
Markdown tracks, reflection, knowledge
- Episodes (user track), agent cases, and foresight live as daily-log
Markdown under
memory/{episodes,cases,foresights}/— append withtools/track.py add ..., search withtrack.py search, never hand-delete (usedeprecate). - Weekly
memory/reflect_episodes.pymerges similar, time-adjacent episodes into one consolidated entry and deprecates the originals (audit inreflection_report.jsonl). Cron it; it is model-free. - Documents become searchable topic pages with
tools/knowledge.py add— source-backed, Markdown, editable;knowledge.py searchbefore answering from memory of a doc. - Durable user facts go through
mem_save_fact(MCP) ormemory/personal/PROFILE.md; trajectories never do. - After a few plan runs:
tools/skill_forge.py clusterthenproposeto turn repeated successful cases into candidate skills for review.
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 Changed · +16 lines ffc6f10bf1a2
- 1mo ago First seen · 51 lines · 2 tokens per session scan A 966dddfc88a6
memory-manager is a skill published in the GitHub repository codejunkie99/agentic-stack (2,302 stars, last pushed 9d ago), licensed Apache-2.0. It adds 2 tokens to every session and 757 once invoked, about $0.0000 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
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.