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/rangerrick337/operator-os/memory-readnpx skills add rangerrick337/operator-os --skill memory-readgit clone --depth 1 https://github.com/rangerrick337/operator-osWrote 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/rangerrick337/operator-os/memory-read)<a href="https://agentmods.dev/skills/rangerrick337/operator-os/memory-read"><img src="https://agentmods.dev/badge/skills/rangerrick337/operator-os/memory-read.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 | $0.00041 | $0.00397 |
| Opus 5 | $0.00020 | $0.00198 |
| Sonnet 5 | $0.00008 | $0.00079 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
memory-read 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 yesterday.
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.
What it actually says
Memory Read
Build an explicit local index, query it, then open only the returned source section. This keeps context small and answers traceable.
Retrieval protocol
- Run
scripts/query.py --query "..."against the generated index. - Never read the complete index,
ACTIVE.md,LONG_TERM.md, or all logs into model context by default. - Open the highest-scoring source section. Follow at most one useful explicit link unless the user asks for a deep dive.
- Return the path, heading, and a concise evidence-based answer.
- If there is no positive match, refine the query; do not present a fallback as evidence.
Commands
Run from the repository root:
python3 "Operator Team OS/3. Skills/memory-read/scripts/build_index.py"
python3 "Operator Team OS/3. Skills/memory-read/scripts/query.py" --query "current priorities"
The default scope is Operator Team OS/6. Memory/ plus Operator Team OS/WIKI.md.
Add a permitted knowledge library explicitly with repeated --include arguments:
python3 "Operator Team OS/3. Skills/memory-read/scripts/build_index.py" \
--include "Operator Team OS/6. Memory" --include "Drive - Example"
Never combine libraries with different permissions into one index. The generated
MEMORY_READ_INDEX.json file is a disposable local cache and must not be treated
as a source of truth or committed.
Memory writes belong to [[memory-manage]]. Rebuild the index after a write.
What ships with it
2 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.
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.
- yesterday First seen · 45 lines · 41 tokens per session scan A e44b4153d0d8
memory-read is a skill published in the GitHub repository rangerrick337/operator-os (10 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 397 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 2026-09-04.
Other skills, from other repositories
honey-memory
Per-project persistent memory files indexed in MEMORY.md.
honey-compress
Rewrite context files terse to cut per-session tokens.
session-end
MUST use when user says 'bye', 'goodbye', 'good night', 'gnight', 'done for today', 'that's all', 'that's it', 'see you', 'see ya', 'let's stop', 'stopping here', 'wrapping up', 'signing off', 'closing down', 'done', 'finished for now', 'talk later', 'cya'. The user does NOT use slash commands; detect these natural…
ctx
Use ctx as working memory for prior agent work. Before starting or continuing work in an unfamiliar area, resuming earlier work, or revisiting an investigation, search prior sessions to ground yourself in earlier context. When ctx blame is available, use it to trace a line, file, commit, or PR to the agent session…
save-session
MUST use when user says 'save', 'save session', or explicitly wants to preserve session state. {USERNAME} does NOT use slash commands; also trigger proactively when significant work has been completed and session context should be persisted. For session endings (bye/done/goodbye), use the session-end skill instead…
load-session
Restore session context at the start of every new conversation. Auto-triggers on session start, or when user says 'continue', 'what were we doing', 'where did we leave off'.