Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/robotaitai/project-bedrocknpx agentmods add skills/robotaitai/project-bedrock/project-memory-writingWrote 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/robotaitai/project-bedrock/project-memory-writing)<a href="https://agentmods.dev/skills/robotaitai/project-bedrock/project-memory-writing"><img src="https://agentmods.dev/badge/skills/robotaitai/project-bedrock/project-memory-writing/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/robotaitai/project-bedrock/project-memory-writing"><img src="https://agentmods.dev/badge/skills/robotaitai/project-bedrock/project-memory-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 37 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00040 | $0.01301 |
| Opus 5.5 | $0.00016 | $0.00520 |
| Sonnet 5.5 | $0.00008 | $0.00260 |
| Haiku 4.5 | $0.00004 | $0.00130 |
Grade A, and why
project-memory-writing 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Memory Writing
Focused rules for writing durable memory notes. This is the craft side of memory management: how to write notes that stay useful across sessions and agents.
When to use this skill
- Creating a new branch note or subtopic note
- Updating Current State or Recent Changes sections
- Reviewing a note that has grown noisy or stale
- Any time the question is "how should I write this?"
For tree structure and reading strategy, see memory-management.
For bootstrapping from scratch, see project-ontology-bootstrap.
Verification first
Before writing anything to Memory/, verify the fact against the source:
| Source type | Verification requirement |
|---|---|
| Code file | Read the actual file, not a cached summary |
| Test | Run it or check its current state in the test output |
| Decision | Confirm it is still active (not reversed) |
| Config | Read the current config file, not old docs |
| Agent output | Treat as hypothesis until confirmed |
Do NOT write:
- Speculative plans
- In-progress task state (use Sessions/)
- Raw agent summaries without verification
- Facts that change faster than once per week
Required frontmatter
Every Memory/ note must open with YAML frontmatter:
---
note_type: <type>
area: <branch-name>
updated: <YYYY-MM-DD>
---
note_type values: durable-memory-root (for MEMORY.md), branch-entry, branch-leaf, decision.
Do not add extra frontmatter fields that tools or other agents don't need.
Required sections for branch notes
Use this section order. Keep each section focused.
## Purpose
One sentence. What this branch covers. Rarely changes.
## Current State
Bullet list of verified facts about what is true right now.
- Lead each bullet with the fact itself.
- Do not describe what you "observed" -- state what IS.
- Each bullet should be independently verifiable.
## Recent Changes
Rolling log. Newest first. YYYY-MM-DD format. Prune to ~8 entries.
- 2025-01-15 - Switched from Prisma to raw SQL. See decisions/.
- 2025-01-10 - Added retry logic to all DB calls.
## Decisions
Links to decision files that affect this area.
- [2025-01-15-use-raw-sql.md](../decisions/2025-01-15-use-raw-sql.md) -- raw SQL over ORM
## Open Questions
Unresolved items. Remove when resolved.
- Why does the worker pool size default to 4? Is this tuned or a placeholder?
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 · 175 lines · 40 tokens per session scan A 4ebb69157341
project-memory-writing is a skill published in the GitHub repository robotaitai/project-bedrock (45 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 1,301 once invoked, about $0.0002 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
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, timelines, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
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…