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/atomicstrata/atomicmemory/clinpx skills add atomicstrata/atomicmemory --skill cligit clone --depth 1 https://github.com/atomicstrata/atomicmemoryWhat 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 | $0.00026 | $0.00383 |
| Opus 5 | $0.00013 | $0.00192 |
| Sonnet 5 | $0.00005 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
atomicmemory-cli 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 2d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 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.
- CHANGELOG.md 420 B
- cli-spec.json 11 KB
- config.schema.json 2.1 KB
- package.json 2.6 KB
- README.md 6.7 KB
- scripts/check-spec-parser-drift.mjs 6.1 KB runs code
- scripts/docker/docker-compose.cli-backend.yml 1.8 KB
- scripts/docker/mock-openai-extraction.mjs 5.8 KB runs code
- scripts/generate-config-schema.mjs 2.9 KB runs code
- scripts/sync-versions.mjs 1.9 KB runs code
- scripts/test-backend-docker.mjs 11 KB runs code
- src/__tests__/adapter-atomicmemory.test.ts 11 KB runs code
- src/__tests__/adapter-mem0.test.ts 4.9 KB runs code
- src/__tests__/adapter-registry.test.ts 2.5 KB runs code
- src/__tests__/adapter-scope-mapper.test.ts 6.7 KB runs code
- src/__tests__/ast-renderer-purity.test.ts 3.6 KB runs code
- src/__tests__/ast-sdk-import-containment.test.ts 2.7 KB runs code
- src/__tests__/backend-gated-smoke.test.ts 14 KB runs code
- src/__tests__/bare-invocation-subprocess.test.ts 2.7 KB runs code
- src/__tests__/capability-gate.test.ts 4.2 KB runs code
- src/__tests__/cli-error-defaults.test.ts 3.0 KB runs code
- src/__tests__/commander-bridge.test.ts 4.7 KB runs code
- src/__tests__/completions.test.ts 6.5 KB runs code
- src/__tests__/config-api-key.test.ts 3.4 KB runs code
- src/__tests__/config-paths.test.ts 1.4 KB runs code
- src/__tests__/config-permissions.test.ts 2.2 KB runs code
- src/__tests__/config-profiles.test.ts 7.3 KB runs code
- src/__tests__/config-resolve.test.ts 4.5 KB runs code
- src/__tests__/config-schema.test.ts 3.1 KB runs code
- src/__tests__/diagnostics-subprocess.test.ts 2.3 KB runs code
- src/__tests__/doctor.test.ts 11 KB runs code
- src/__tests__/dynamic-scope-extras.test.ts 6.7 KB runs code
- src/__tests__/dynamic-scope.test.ts 3.8 KB runs code
- src/__tests__/envelope.test.ts 2.9 KB runs code
- src/__tests__/filter-json-early-fail.test.ts 2.4 KB runs code
- src/__tests__/hooks-agent-sanitizer.test.ts 2.0 KB runs code
- src/__tests__/hooks-command.test.ts 14 KB runs code
- src/__tests__/hooks-env-limits.test.ts 3.7 KB runs code
- src/__tests__/hooks-install-notes.test.ts 4.1 KB runs code
- src/__tests__/hooks-prompt-context.test.ts 10 KB runs code
- src/__tests__/hooks-sanitize.test.ts 18 KB runs code
- src/__tests__/import-llmwiki-subprocess.test.ts 3.7 KB runs code
- src/__tests__/import-llmwiki.test.ts 13 KB runs code
- src/__tests__/ingest-content-class-flag.test.ts 1.5 KB runs code
- src/__tests__/init-apiurl.test.ts 6.8 KB runs code
- src/__tests__/ink-launch.test.ts 3.6 KB runs code
- src/__tests__/input-precedence.test.ts 3.5 KB runs code
- src/__tests__/interactive-dashboard.test.ts 15 KB runs code
- src/__tests__/interactive-detect.test.ts 2.1 KB runs code
- src/__tests__/lifecycle-order.test.ts 8.0 KB runs code
- src/__tests__/limits.test.ts 2.3 KB runs code
- src/__tests__/machine-output-subprocess.test.ts 5.8 KB runs code
- src/__tests__/output-mode-resolution.test.ts 1.2 KB runs code
- src/__tests__/phase5-paths.test.ts 10 KB runs code
- src/__tests__/profile-resolution.test.ts 1.6 KB runs code
- src/__tests__/sanitizer-coverage.test.ts 1.5 KB runs code
- src/__tests__/sanitizer-redaction.test.ts 5.7 KB runs code
- src/__tests__/spec-coverage.test.ts 3.0 KB runs code
- src/__tests__/spec-loader.test.ts 3.2 KB runs code
- src/__tests__/subprocess-smoke.test.ts 17 KB runs code
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.
- 2d ago First seen · 32 lines · 26 tokens per session scan A e7e499c0820c
atomicmemory-cli is a skill published in the GitHub repository atomicstrata/atomicmemory (429 stars, last pushed 5d ago), with no licence file. It adds 26 tokens to every session and 383 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 2026-08-30.
Other skills, from other repositories
memseek-feedback
Record success, failure, or a correction against the Memseek context used for the latest request.
memseek-status
Diagnose the Memseek Claude Code connection, project identity, MCP tool package, and queued writes.
memseek-remember
Persist a user-confirmed fact, preference, constraint, or decision in Memseek project memory.
memseek-explain
Audit why Memseek recalled a claim by opening its evidence and replaying the original session when needed.
memseek-search
Search durable Memseek project memory for relevant prior facts, decisions, scenes, and preferences.
data_analysis
基于已确认数据执行可审计的数学计算和描述统计。.