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 skills add RudraDudhat2509/claude-skills --skill session-docsgit clone --depth 1 https://github.com/RudraDudhat2509/claude-skillsWrote 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/rudradudhat2509/claude-skills/session-docs)<a href="https://agentmods.dev/skills/rudradudhat2509/claude-skills/session-docs"><img src="https://agentmods.dev/badge/skills/rudradudhat2509/claude-skills/session-docs/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/rudradudhat2509/claude-skills/session-docs"><img src="https://agentmods.dev/badge/skills/rudradudhat2509/claude-skills/session-docs.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 | $0.00038 | $0.00949 |
| Opus 5.5 | $0.00015 | $0.00380 |
| Sonnet 5.5 | $0.00008 | $0.00190 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade A, and why
session-docs 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Documentation Skill
Run this at the end of every session. The goal is a memory system that is always accurate and never redundant — future sessions should be able to pick up exactly where this one left off without re-reading the conversation.
What this skill does
- Scans the session for what's worth saving
- Identifies which memory files need changes
- Writes immediately — no proposal, no approval gate
Step 1 — Scan the session
Go through the conversation and extract only things that fit one of these three categories:
Outdated status — something was PENDING and is now DONE, or was assumed working and broke, or a decision was reversed. Status that doesn't match reality is the most damaging type of stale memory.
Missing decisions — a non-obvious choice was made and the WHY isn't captured anywhere. If someone reads the code in 3 months, will they understand why this approach was taken? If not, it belongs in memory.
Stale file paths / function names — a file was renamed, moved, deleted, or a key function changed its name or signature. Memory that points to a ghost is worse than no memory at all.
Do NOT capture:
- Things that are obvious from reading the code or running
git log - In-progress work that isn't settled yet
- Error messages and debugging steps (the fix is in the code)
- Anything already in CLAUDE.md
- Temporary state from this session only
Graphify context (check every session)
All three altagic codebases have persistent knowledge graphs in graphify-out/ directories:
| Project | Path | Last known stats |
|---|---|---|
| Color Tool | Color_tool/graphify-out/ |
452 nodes, 710 edges, 43 communities |
| HR Dashboard | hr_dashboard/graphify-out/ |
609 nodes, 861 edges, 42 communities |
| Drapeme Pipeline | drapeme-pipeline/graphify-out/ |
216 nodes, 425 edges, 14 communities |
Each directory contains: graph.html (interactive vis.js), graph.json (GraphRAG-ready), GRAPH_REPORT.md.
If a session built or updated any of these graphs, record the new node/edge counts in memory. If the session made significant structural changes to a codebase (new modules, renamed files, deleted components), note that the graph is stale and should be rebuilt with /graphify <path> before the next deep codebase question.
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 · 78 lines · 0 tokens per session scan A 9d5a3d7e7b58
session-docs is a skill published in the GitHub repository RudraDudhat2509/claude-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 949 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 2026-08-31.
Other skills, from other repositories
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory CLI for Hermes Agent. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory for MiniMax Code. Recall durable context, store important facts and decisions, and link related memories with the mnemon CLI.
durable-session-state
Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.