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/takaok5/codex-project-memory/repo-memorynpx skills add takaok5/codex-project-memory --skill repo-memorygit clone --depth 1 https://github.com/takaok5/codex-project-memoryWrote 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/takaok5/codex-project-memory/repo-memory)<a href="https://agentmods.dev/skills/takaok5/codex-project-memory/repo-memory"><img src="https://agentmods.dev/badge/skills/takaok5/codex-project-memory/repo-memory.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.00787 |
| Opus 5 | $0.00009 | $0.00394 |
| Sonnet 5 | $0.00004 | $0.00157 |
| Haiku 4.5 | $0.00002 | $0.00079 |
Grade A, and why
repo-memory 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 5d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Memory
Use this skill when working in a repository that has Codex Project Memory installed.
Core workflow
- Prefer
memory.agentfor project-memory lifecycle orchestration. - Use granular tools only when debugging or when a narrower read is enough.
- Before creating a service, controller, DTO, route, table, module, repository, adapter, job or utility, pass an
artifacttomemory.agent. - Start from
contextPack.evidence,contextPack.budget,contextPack.decisions, impact and conflict output before broad repository search. - After changes, use
memory.agentwithphase: "post_change"orpmem agent run --phase post_change --json. - Use persisted runtime evidence and feedback to improve later retrieval instead of adding a second memory MCP server.
memory.agent is a single MCP entrypoint with internal specialized agents:
intent router, evidence retriever, duplicate sentinel, impact assessor, runtime evidence importer, writer gate, conflict arbiter and context compressor.
The agent persists a bounded evidence ledger in the project-local SQLite store: accepted evidence, rejected candidates, duplicate risks, runtime evidence, invalidable architecture decisions and feedback signals. Conversation text is not stored as memory; intents are hashed where feedback/logs need correlation.
Supported lifecycle
Codex app plugin validation does not currently accept plugin-declared hooks. Use this implicit skill plus MCP tools as the supported project lifecycle:
- Prompt start: call
memory.agentwithphase: "pre_task". - Implementation intent: call
memory.agentwith the user request before editing. - New artifact intent: call
memory.agentwithphase: "pre_create"andartifact. - After source changes: call
memory.agentwithphase: "post_change". - Visual orientation: call
memory.agentwithphase: "orient". - Review/closeout: call
memory.agentwithphase: "review".
Granular fallback tools: memory.head, memory.query, memory.duplicates, memory.frame, memory.refresh, memory.diff.
What ships with it
1 file 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.
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.
- 5d ago First seen · 70 lines · 18 tokens per session scan A db84922621c1
repo-memory is a skill published in the GitHub repository takaok5/codex-project-memory (0 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 787 once invoked, about $0.0001 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 skills, from other repositories
codex-native-memory
Search local Codex cross-session memory when the user asks what happened in other chats, wants project continuity, or asks to recall prior Codex work.
session-handoff
Synthesizes the current session into a structured HANDOFF block for context transfer between sessions. Captures what was built, decisions made, and unresolved items.
docmancer
Work from the same local memory as every other coding agent on this machine. Recall prior decisions, preferences, instructions, and project conventions that Claude Code, Codex, Cursor, and other agents wrote here, with cited sources, fully local. Also searches a separate local technical-documentation index.
fd-audit
Audit a change for resource leaks in OpenAlgo — file descriptors AND unbounded memory growth. Run after building a feature or fixing anything that touches databases, WebSockets or streaming, threads or executors, subprocesses, files, sockets, caches, or module-level registries. Also use when the user reports "too many…
memory-layer
Standalone persistent memory for Pi — smart search, symbol clustering, dedup, auto-recovery, trust scoring. Zero Python dependency.
state-memory-mcp
Teaches the agent to use the state-memory-mcp MCP server to track workflow state, tasks, decisions, blockers, artifacts, plans, milestones, and their semantic relationships in a persistent graph database.