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 umangbuilds/dhurandhar-os --skill soul-keepergit clone --depth 1 https://github.com/umangbuilds/dhurandhar-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/umangbuilds/dhurandhar-os/soul-keeper)<a href="https://agentmods.dev/skills/umangbuilds/dhurandhar-os/soul-keeper"><img src="https://agentmods.dev/badge/skills/umangbuilds/dhurandhar-os/soul-keeper/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/umangbuilds/dhurandhar-os/soul-keeper"><img src="https://agentmods.dev/badge/skills/umangbuilds/dhurandhar-os/soul-keeper.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 | $0.00204 | $0.03711 |
| Opus 5 | $0.00102 | $0.01855 |
| Sonnet 5 | $0.00041 | $0.00742 |
| Haiku 4.5 | $0.00020 | $0.00371 |
Grade A, and why
soul-keeper 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 12d 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Soul Keeper
The identity, voice, and memory layer for DhurandharOS. Soul Keeper is the foundation every other skill leans on. Without it, Builder ships in the wrong voice, Reviewer outputs in the wrong tone, PRD Writer assumes US-default frames.
This skill activates on three classes of trigger: session start (load identity), memory or lesson markers (capture state), and session end (offer to digest the session into MEMORY/lessons).
When this skill activates
Auto-trigger conditions (natural language):
- Session start — fresh Claude Code session in a directory with
SOUL.md,STYLE.md,IDENTITY.mdpresent. - "Remember this," "log this," "save for later," "important," "for next time" — capture to MEMORY.md.
- "Lesson learned," "next time," "we should have," "I should have" — capture to lessons.md.
- Session end — operator says "closing out," "done for the day," "wrapping up," or invokes
/exitequivalent — propose digest.
Explicit invocation: "use soul-keeper to capture this," "save this to memory," "log this lesson."
Does not activate on: code generation, security review, spec writing, brainstorming, hiring. Those have their own skills. Soul Keeper does the identity and memory plumbing only.
Session-start ritual
When a fresh session opens, run this sequence before responding to anything. DhurandharOS identity is shipped, never configured. The skill must always find the identity files — either in the working directory (project override) or in the plugin cache (default).
File-resolution order — for each of SOUL.md, STYLE.md, IDENTITY.md, MEMORY.md, lessons.md:
- First check the user's working directory (project root).
- If not present, fall back to the plugin cache. The cache path is:
Discover the latest version dynamically — run~/.claude/plugins/cache/dhurandhar-os/dhurandhar-os/<latest-version>/ls ~/.claude/plugins/cache/dhurandhar-os/dhurandhar-os/ | sort -V | tail -1and use the result as the version directory. - Working-directory file always wins over cache file when both exist (project-specific override).
- If the cache itself is missing (the directory does not exist), surface a clear reinstall instruction — see "Cache-missing failure mode" below. Never pivot to "let me build your identity from scratch."
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.
- 12d ago First seen · 247 lines · 204 tokens per session scan A bea92c09f59c
soul-keeper is a skill published in the GitHub repository umangbuilds/dhurandhar-os (1 stars, last pushed 4mo ago), licensed MIT. It adds 204 tokens to every session and 3,711 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
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…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.