Borrowing it
Nothing to install: this file belongs to SamuelBagattin/concerts-paris-mcp. 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/SamuelBagattin/concerts-paris-mcp/main/.claude/skills/project-memory/SKILL.mdgit clone --depth 1 https://github.com/SamuelBagattin/concerts-paris-mcpWrote 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/samuelbagattin/concerts-paris-mcp/project-memory)<a href="https://agentmods.dev/skills/samuelbagattin/concerts-paris-mcp/project-memory"><img src="https://agentmods.dev/badge/skills/samuelbagattin/concerts-paris-mcp/project-memory/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/samuelbagattin/concerts-paris-mcp/project-memory"><img src="https://agentmods.dev/badge/skills/samuelbagattin/concerts-paris-mcp/project-memory.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 | $0.00098 | $0.00877 |
| Opus 5 | $0.00049 | $0.00439 |
| Sonnet 5 | $0.00020 | $0.00175 |
| Haiku 4.5 | $0.00010 | $0.00088 |
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 11d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Memory Maintenance
Three files, three jobs. Be ruthless about brevity. Token cost compounds — every line you add is paid every future session.
When invoked
Decide which mode applies:
- Log mode (default at end of work unit): append to JOURNAL.md, propagate any architectural decisions to ARCHITECTURE.md, update PROJECT.md only if status/scope shifted.
- Audit mode (user says "review memory" or roughly every 10 sessions): self-improvement pass over all four files.
Log mode
1. JOURNAL.md — append, never rewrite
Prepend a new entry at the top of the entries (under the file header):
## YYYY-MM-DD — <one-line title summarizing the work>
- **Did:** <2–4 concrete bullets>
- **Why:** <1 line, only if non-obvious>
- **Decisions:** <only if architectural — also propagate to ARCHITECTURE.md>
- **Open:** <known unfinished threads>
- **Lessons:** <only if Claude got something wrong and was corrected>
Use today's actual date. If nothing meaningful happened, write **Did:** housekeeping — do not inflate.
If JOURNAL.md exceeds ~80 active entries (excluding the backfill section), move the oldest quarter's entries to docs/journal-archive/YYYY-QN.md.
2. ARCHITECTURE.md — update only if a decision was made
If the work unit produced an architectural decision (stack change, structural choice, library swap, pattern adoption), prepend to "Key decisions":
### YYYY-MM-DD — <decision title>
<One paragraph: what was decided, why, what was rejected.>
Update Stack/Structure/Conventions/Known gotchas sections inline if reality changed. Replace stale content; do not append duplicates.
3. PROJECT.md — update only if scope/status shifted
If today's work changed Status, Scope-in, Scope-out, or Next milestone, edit those sections in place. Otherwise leave it alone.
Audit mode (self-improvement)
Triggered by "review memory" or proactively every ~10 sessions if the user agrees.
- Read the last 10 JOURNAL.md entries (skip the historical backfill section), plus PROJECT.md, ARCHITECTURE.md, CLAUDE.md.
- Identify:
- Repeated lessons (same correction across multiple journal entries) → promote to ARCHITECTURE.md > Conventions or to CLAUDE.md > Hard rules.
- Unrecorded decisions — decisions visible in the journal but missing from ARCHITECTURE.md > Key decisions.
- Drifted PROJECT.md — claims that no longer match what the journal shows happened.
- Violated CLAUDE.md rules — rules that were broken more than once → reword more sharply or strengthen with
IMPORTANT:prefix. - Stale
_(verify)_markers from the original migration → confirm or correct. - Bloat — sections in any file that have grown past their useful size.
- Show a unified diff of proposed changes. Wait for approval before writing.
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.
- 11d ago First seen · 73 lines · 98 tokens per session scan A 69f669c433a4
project-memory is a skill published in the GitHub repository SamuelBagattin/concerts-paris-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 877 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 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
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.…
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.