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 skills/tenureai/phd-zero/memory-managernpx skills add TenureAI/PhD-Zero --skill memory-managergit clone --depth 1 https://github.com/TenureAI/PhD-ZeroWhat 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 | $0.00099 | $0.02313 |
| Opus 5 | $0.00049 | $0.01156 |
| Sonnet 5 | $0.00020 | $0.00463 |
| Haiku 4.5 | $0.00010 | $0.00231 |
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 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Manager
Mission
Build compounding capability by turning execution traces into reusable, evidence-linked memory, with retrieval centered on prior experience rather than only current working state.
Load References
Load these files before writing or promoting records:
references/memory-layout.mdreferences/memory-templates.mdreferences/sqlite-schema.sql
Memory Types
Manage these layers:
working- run-scoped continuity state
- resume after compaction, interruption, or long waits
episode- concrete run case records
- useful for similar errors, repeated attempts, and local history
procedure- highest-priority execution memory
- default retrieval layer before acting
insight- cross-task abstraction, tradeoffs, boundaries, and contradiction handling
persona- behavior config only
Working Memory Contract
working must include:
goalstagehypothesislast_actionlast_observationnext_stepblockersevidence_refsactive_action_idstodo_activetodo_donetodo_blocked
Todo granularity should be task-level (small stages/subtasks), not command-level.
Experience-First Retrieval Policy
Prior experience retrieval is the default. working is important for continuity, but it is not the only retrieval path and should not crowd out reusable experience.
Mandatory retrieval triggers:
- every new user turn
- every execution batch before acting
- every replan
- every significant failure or new error signature
- every high-resource or irreversible action
- every long-action resume or post-poll decision
- before final answer or report handoff
- when modifying
memory-manageror another Memory-related skill/instruction - when compaction markers such as
Compact,压缩, orSummaryappear
Default retrieval order:
procedure- mandatory before every execution batch
episode- mandatory when a similar failure, repeated attempt, or same task type is present
insight- mandatory during planning, tradeoff analysis, contradiction handling, or final answer shaping
working- mandatory for resume, compaction recovery, long-action reconciliation, and final handoff
What ships with it
9 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 463 B
- references/memory-layout.md 979 B
- references/memory-templates.md 1.2 KB
- references/sqlite-schema.sql 1.5 KB
- scripts/memory_store.py 7.5 KB runs code
- scripts/retrieve_local_memory.py 2.6 KB runs code
- scripts/retrieve_working_state.py 1.0 KB runs code
- scripts/shared_memory_retrieval.py 8.8 KB runs code
- scripts/write_working_delta.py 2.8 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.
- 2d ago First seen · 277 lines · 99 tokens per session scan A ad34879eea88
memory-manager is a skill published in the GitHub repository TenureAI/PhD-Zero (52 stars, last pushed 5mo ago), licensed MIT. It adds 99 tokens to every session and 2,313 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
auto-paper-improvement-loop
Autonomously improve a generated paper via GPT-5.4 xhigh review → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.
citation-audit
Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports. Uses a fresh cross-model reviewer with web/DBLP/arXiv lookup to catch hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context…
grant-proposal
Draft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including 面上/青年/优青/杰青/海外优青/重点), ERC (EU), DFG (Germany), SNSF (Switzerland), ARC (Australia), NWO (Netherlands), and generic formats. Use when user says "write grant", "grant proposal", "申請書", "write…
paper-illustration
Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.
paper-navigator
Find and read academic papers: disambiguate queries, discover papers (search, citation traversal, recommendations, arXiv monitoring, trending, GitHub search), evaluate (TLDR, citations, code, SOTA), and read with structured analysis (3-level strategy). Use when: finding papers, reading a paper, related work, citation…
paper-write
Draft LaTeX paper section by section from an outline. Use when user says "写论文", "write paper", "draft LaTeX", "开始写", or wants to generate LaTeX content from a paper plan.