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/anombyte93/atlas-session-lifecycle/syncnpx skills add anombyte93/atlas-session-lifecycle --skill syncgit clone --depth 1 https://github.com/anombyte93/atlas-session-lifecycleWhat 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 | $0.00049 | $0.00690 |
| Opus 5 | $0.00024 | $0.00345 |
| Sonnet 5 | $0.00010 | $0.00138 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
sync 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync
Zero questions. Edit files. Print summary. Done.
Rules
- No questions — never ask the user anything. Just save.
- No subagents — run entirely in the main thread.
- No MCP tools — direct file reads and edits only (faster).
- No narration — don't announce steps. Just do them.
- Touch every file — even if only adding a timestamp entry.
- Speed over perfection — a rough sync beats no sync.
Execute
Use the current time formatted as HH:MM DD/MM/YY for the checkpoint header.
1. Edit session-context/CLAUDE-activeContext.md
Append a new section at the end:
## [SYNC] {time}
**Accomplished:**
- {bullet list of what was done this session}
**In progress:**
- {what's currently being worked on}
**Next steps:**
- {what comes next}
**Blockers:**
- {any blockers, or "None"}
2. Edit session-context/CLAUDE-decisions.md
Append new decisions made this session. If none, append:
## {time}
No new decisions this session.
3. Edit session-context/CLAUDE-patterns.md
Append new patterns discovered. If none, append:
## {time}
No new patterns this session.
4. Edit session-context/CLAUDE-troubleshooting.md
Append new issues and solutions. If none, append:
## {time}
No new issues this session.
5. Update MEMORY.md
Update the auto-memory file at the project memory path with any new learnings from this session. If nothing new, skip this file (memory should stay concise).
6. Print summary
Print exactly one block:
Synced. {N} files updated.
- Active context: {1-line summary of what was captured}
- Decisions: {count new or "no new"}
- Patterns: {count new or "no new"}
- Troubleshooting: {count new or "no new"}
- Memory: {updated or "no changes"}
/sync --full (Capability Inventory)
Extended sync that includes capability inventory generation.
Execute
- Run standard sync flow (Steps 1-5 above).
- Call
session_capability_inventory(project_dir, force_refresh=True)— bypasses cache and regenerates inventory even if git unchanged. - If
needs_generation == True: the MCP tool will generate the inventory. - Read
CLAUDE-capability-inventory.mdif it exists.
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.
- 3d ago First seen · 114 lines · 49 tokens per session scan A ffd069bfffe2
sync is a skill published in the GitHub repository anombyte93/atlas-session-lifecycle (88 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 690 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 2026-08-30.
Other skills, from other repositories
session-orchestrator
Session orchestrator on top of the recall index of all Claude Code sessions: finds a past session by task description, dives in (context, project, skill, artifacts) and acts in one of three modes — finish here, hand off the resume command, or open the session in a new terminal window. Use when user asks: "find the…
clinpgx-database
Access ClinPGx pharmacogenomics data (successor to PharmGKB). Query gene-drug interactions, CPIC guidelines, allele functions, for precision medicine and genotype-guided dosing decisions.
data-quality-frameworks
Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.
coding-tutor
Personalized coding tutorials that build on your existing knowledge and use your actual codebase for examples. Creates a persistent learning trail that compounds over time using the power of AI, spaced repetition and quizes.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
data-artist
Create beautiful data visualizations with mathematical elegance, color theory, and narrative design - the "Data is Beautiful" aesthetic.