project-memory

project-memory is a skill for Claude Code, Codex from mtvrkan/senior-dev-kit. It costs 39 tokens per session (426 once invoked), scanned A, original, MIT.

A project memory file for durable facts that future coding sessions need, such as decisions, conventions, unresolved questions, and non-obvious problems. It is separate from a developer's personal memory.

In plain words
What is it for?
Use it to maintain dated notes in a project's .claude/PROJECT-MEMORY.md file, updating existing entries about decisions, gotchas, conventions, and open questions without changing code.
Why use it?
It prevents future sessions from rediscovering important context or repeating known mistakes. It records only facts that could affect a later decision and excludes secrets and personal data.

Skill for Claude CodeCodex

Part of the senior-dev-kit plugin — 25 skills, 6 commands, 9 agents, 1 hook shipped together

Install

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.

agentmods
npx agentmods add skills/mtvrkan/senior-dev-kit/project-memory
Any agent
npx skills add mtvrkan/senior-dev-kit --skill project-memory
Clone the repo
git clone --depth 1 https://github.com/mtvrkan/senior-dev-kit

Made for: Claude Code, Codex.

Or install senior-dev-kit, the plugin that ships this one along with the rest of its 25 skills, 6 commands, 9 agents, 1 hook.

Wrote 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.

agentmods badge for project-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/mtvrkan/senior-dev-kit/project-memory.svg)](https://agentmods.dev/skills/mtvrkan/senior-dev-kit/project-memory)
Your own site
<a href="https://agentmods.dev/skills/mtvrkan/senior-dev-kit/project-memory"><img src="https://agentmods.dev/badge/skills/mtvrkan/senior-dev-kit/project-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 426 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00039 $0.00426
Opus 5 $0.00019 $0.00213
Sonnet 5 $0.00008 $0.00085
Haiku 4.5 $0.00004 $0.00043

Measured 3d ago against content hash c46b5bb1fdf8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-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 3d 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.

skills/project-memory/SKILL.md · 22 lines

What it actually says

project-memory

Maintain .claude/PROJECT-MEMORY.md — durable project facts not in the code or git history (why a decision was made, a footgun that cost time, a convention written nowhere else). Not personal preferences — that's the user's own ~/.claude memory, out of scope here.

  1. Read the existing file first if present — update/extend an entry, never duplicate it.
  2. Structure as dated bullets under ## Decisions / ## Gotchas / ## Conventions / ## Open questions — one line each, with a one-clause "why."
  3. Write only what would change a future decision or prevent repeating a mistake — skip what's obvious from the code.
  4. Never record secrets, credentials, or PII, even paraphrased inside a decision/gotcha note — write "rotated the prod DB credential after a leak" not the credential itself, "tenant X hit the null-address bug" not their email. Same NEVER READ OR OUTPUT list as everywhere else in the kit.
  5. At session start, read the file before unfamiliar work if it exists; verify stale-looking entries against current code before acting on them.
  6. Trigger on: "remember this" / "note this for later," before a planned /clear with unresolved context, or after a confirmed architecture decision / resolved non-obvious bug.
  7. Keep the file under ~150 lines — propose trimming superseded entries instead of appending forever.
Changes

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.

  1. 3d ago First seen · 22 lines · 39 tokens per session scan A c46b5bb1fdf8

Subscribe to this mod's changes

project-memory is a skill published in the GitHub repository mtvrkan/senior-dev-kit (5 stars, last pushed 14d ago), licensed MIT. It adds 39 tokens to every session and 426 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

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…

danielmiessler/LifeOS · 196 tokens

auditing-subgroup-fairness

Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…

maziyarpanahi/openmed · 148 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

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.

opensquilla/opensquilla · 44 tokens

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…

shiwenwen/hope-agent · 115 tokens