Borrowing it
Nothing to install: this file belongs to TenureAI/PhD-Zero. 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/TenureAI/PhD-Zero/main/.agents/skills/memory-manager/SKILL.mdgit clone --depth 1 https://github.com/TenureAI/PhD-ZeroWrote 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/tenureai/phd-zero/memory-manager)<a href="https://agentmods.dev/skills/tenureai/phd-zero/memory-manager"><img src="https://agentmods.dev/badge/skills/tenureai/phd-zero/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/tenureai/phd-zero/memory-manager"><img src="https://agentmods.dev/badge/skills/tenureai/phd-zero/memory-manager.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 | $0.00099 | $0.02313 |
| Opus 5.5 | $0.00040 | $0.00925 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 (53 stars, last pushed 7mo ago), licensed MIT. It adds 99 tokens to every session and 2,313 once invoked, about $0.0004 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
evo-memory
Manages persistent research memory across ideation and experimentation cycles. Maintains two stores: Ideation Memory MI (feasible/unsuccessful directions) and Experimentation Memory ME (reusable strategies for data processing, model training, architecture, debugging). Three evolution mechanisms: IDE (after…
research-wiki
A persistent research knowledge base for storing papers, ideas, experiments, claims, and the links between them. It keeps this information available across the research process.
auto-paper-improvement-loop
An automated loop for improving a generated research paper through repeated review, editing, and recompilation. Recompiling rebuilds the paper so changes can be checked in the final document.
proof-checker
A rigorous proof-checking and repair skill for LaTeX mathematics. LaTeX is a text format commonly used to write mathematical documents.
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
A grant-writing workflow that turns research ideas and related literature into structured funding proposals for named national and international grant formats.