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 paulrobello/parsidion --skill parsidiongit clone --depth 1 https://github.com/paulrobello/parsidionWrote 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/paulrobello/parsidion/parsidion)<a href="https://agentmods.dev/skills/paulrobello/parsidion/parsidion"><img src="https://agentmods.dev/badge/skills/paulrobello/parsidion/parsidion/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/paulrobello/parsidion/parsidion"><img src="https://agentmods.dev/badge/skills/paulrobello/parsidion/parsidion.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 | $0.00242 | $0.10736 |
| Opus 5 | $0.00121 | $0.05368 |
| Sonnet 5 | $0.00048 | $0.02147 |
| Haiku 4.5 | $0.00024 | $0.01074 |
Grade B, and why
parsidion scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Claude Code installs the full hook set below. Codex runtime hooks are session lifecycle only: native Codex `SessionStart` and `Stop` hooks registered in `~/.codex/hooks.json` when `hooks = true` is enabled in `~/.codex/c How it starts
The opening of the file, as written. The whole thing — 746 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parsidion vault - Knowledge Management System
A richly organized Obsidian vault (default
~/ParsidionVault/, with legacy~/ClaudeVault/fallback) that replaces built-in auto memory with structured, searchable, cross-linked knowledge.
Philosophy
- Search before create. Always search the vault before creating a new note. Duplicate knowledge fragments rot.
- Atomic notes. One concept per note. If a note covers two distinct ideas, split it.
- Frontmatter is mandatory. Every note must have a valid YAML frontmatter block. No exceptions.
- Knowledge compounds. Individual notes gain value through links. An unlinked note is a dead note.
- Confidence matters. Tag what you know vs. what you suspect. Update confidence as understanding deepens.
Vault-First Consultation
The vault is your first stop — not your last resort. Before web search, before documentation, before experimentation, check whether the vault already holds a solution.
Debugging: Search Before You Diagnose
When you encounter an error, exception, or unexpected behavior:
- Extract the key signal: the exception type, package name, or the most distinctive phrase from the error message
- Dispatch the
vault-exploreragent with the signal as the query. - Answer returned? Apply the documented solution; update the note if you learn something new about the problem.
Readspecific files from the Sources section only if you need more depth. - "No relevant vault notes found"? Diagnose, solve, then save the solution so future sessions benefit.
Implementation: Check for Prior Art
When implementing any feature, pattern, or integration:
- Dispatch the
vault-exploreragent with the feature keyword as the query. - Answer returned? Reuse and adapt — a proven implementation beats a fresh one every time.
Readspecific files from the Sources section for details; check thesourcesfrontmatter field for code references. - "No relevant vault notes found"? Implement it, then save the pattern so future sessions benefit.
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.
- AGENT_INSTRUCTIONS.md 611 B
- scripts/agent_adapter.py 55 KB runs code
- scripts/ai_backend.py 714 B runs code
- scripts/antigravity_session_end_hook.py 2.5 KB runs code
- scripts/antigravity_session_start_hook.py 2.7 KB runs code
- scripts/build_embeddings.py 24 KB runs code
- scripts/build_graph.py 40 KB runs code
- scripts/check_graph_coverage.py 7.6 KB runs code
- scripts/cli/__init__.py 954 B runs code
- scripts/cli/index/__init__.py 2.4 KB runs code
- scripts/cli/index/_common.py 736 B runs code
- scripts/cli/index/build.py 13 KB runs code
- scripts/cli/index/cli.py 2.2 KB runs code
- scripts/cli/index/db.py 3.4 KB runs code
- scripts/cli/index/graph.py 4.1 KB runs code
- scripts/cli/index/models.py 2.9 KB runs code
- scripts/cli/index/parse.py 3.6 KB runs code
- scripts/cli/index/render.py 4.1 KB runs code
- scripts/cli/merge/__init__.py 2.8 KB runs code
- scripts/cli/merge/ai_helpers.py 3.7 KB runs code
- scripts/cli/merge/display.py 1.9 KB runs code
- scripts/cli/merge/frontmatter.py 1.8 KB runs code
- scripts/cli/merge/index.py 2.3 KB runs code
- scripts/cli/merge/lookup.py 2.4 KB runs code
- scripts/cli/merge/preview.py 3.2 KB runs code
- scripts/cli/merge/scan.py 6.2 KB runs code
- scripts/cli/search/__init__.py 1.8 KB runs code
- scripts/cli/search/_common.py 3.5 KB runs code
- scripts/cli/search/embeddings.py 19 KB runs code
- scripts/cli/search/format.py 3.6 KB runs code
- scripts/cli/search/metadata.py 12 KB runs code
- scripts/cli/stats/__init__.py 1.8 KB runs code
- scripts/cli/stats/_common.py 2.2 KB runs code
- scripts/cli/stats/cli.py 14 KB runs code
- scripts/cli/stats/dashboard.py 5.4 KB runs code
- scripts/cli/stats/graph.py 3.9 KB runs code
- scripts/cli/stats/health.py 1.6 KB runs code
- scripts/cli/stats/operations.py 13 KB runs code
- scripts/cli/stats/overview.py 5.0 KB runs code
- scripts/cli/stats/rollups.py 7.8 KB runs code
- scripts/cli/stats/summary.py 2.6 KB runs code
- scripts/codex_session_start_hook.py 782 B runs code
- scripts/codex_stop_hook.py 756 B runs code
- scripts/codex_subagent_stop_hook.py 776 B runs code
- scripts/core/__init__.py 859 B runs code
- scripts/core/ai_backend.py 39 KB runs code
- scripts/core/parsight_backend.py 42 KB runs code
- scripts/core/rule_triggers.py 5.0 KB runs code
- scripts/core/subproc_util.py 6.0 KB runs code
- scripts/core/transcript_reader.py 7.8 KB runs code
- scripts/core/vault_adaptive.py 10.0 KB runs code
- scripts/core/vault_config.py 29 KB runs code
- scripts/core/vault_constants.py 1.5 KB runs code
- scripts/core/vault_fs.py 50 KB runs code
- scripts/core/vault_health.py 34 KB runs code
- scripts/core/vault_hooks.py 26 KB runs code
- scripts/core/vault_index.py 63 KB runs code
- scripts/core/vault_links.py 25 KB runs code
- scripts/core/vault_metrics.py 25 KB runs code
- scripts/core/vault_path.py 35 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 Changed · +2 lines 6efc792f8c45
- 6d ago Changed 9b6a0c4e6885
- 11d ago First seen · 744 lines · 242 tokens per session scan B d3821ac24588
parsidion is a skill published in the GitHub repository paulrobello/parsidion (10 stars, last pushed 2d ago), licensed MIT. It adds 242 tokens to every session and 10,736 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.