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 JakubMikolajek/codex-skills-collection --skill knowledge-retrievalgit clone --depth 1 https://github.com/JakubMikolajek/codex-skills-collectionWrote 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/jakubmikolajek/codex-skills-collection/knowledge-retrieval)<a href="https://agentmods.dev/skills/jakubmikolajek/codex-skills-collection/knowledge-retrieval"><img src="https://agentmods.dev/badge/skills/jakubmikolajek/codex-skills-collection/knowledge-retrieval/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/jakubmikolajek/codex-skills-collection/knowledge-retrieval"><img src="https://agentmods.dev/badge/skills/jakubmikolajek/codex-skills-collection/knowledge-retrieval.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 | $0.00094 | $0.01841 |
| Opus 5 | $0.00047 | $0.00920 |
| Sonnet 5 | $0.00019 | $0.00368 |
| Haiku 4.5 | $0.00009 | $0.00184 |
Grade A, and why
knowledge-retrieval 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Retrieval
This skill is the read side of the vault. obsidian-note writes durable knowledge;
this skill retrieves it back into task context, bounded and justified, instead of either ignoring
the vault entirely or dumping it wholesale into a prompt.
When to Use
- Before
architecture-designor/plan, when the project has an established vault with_index.md/_context.mdalready populated - Before implementing something that plausibly has prior art in the vault (a pattern, a playbook, an ADR that already decided this trade-off)
- When a debug task's symptom resembles something in
04-debug/or03-skills/playbooks/
When NOT to Use
- No vault configured yet (
_codex-config.mdmissing) — nothing to retrieve - Purely trivial task with no plausible prior art
- The task already has an explicit, sufficient context (don't re-fetch what's already in hand)
Core Principle: Bounded, Justified, Degradable
- Bounded: return 3-7 notes/snippets within an explicit token budget (default: treat ~1500 tokens of note content as the ceiling for a normal task; state the number used when it differs). Never return "everything that matched" — rank and cut.
- Justified: every note in the pack gets one line saying why it was selected. A context pack with unexplained inclusions is not trustworthy enough to hand to an implementer.
- Degradable: this skill must work with nothing more than the filesystem and
grep/keyword search. Treat semantic ranking as an enhancement layered on top when available, never a precondition for functioning at all.
Retrieval Process
Knowledge Retrieval progress:
- [ ] Step 1: Read the project's _context.md and _index.md
- [ ] Step 2: Gather candidates
- [ ] Step 3: Rank candidates
- [ ] Step 4: Cut to budget
- [ ] Step 5: Return the context pack with reasons
Step 1: Read _context.md and _index.md first
These are the cheapest, highest-value reads — _context.md (see obsidian-note's
references/context-file.md) already summarizes current state, constraints, and known traps.
Read them before anything else; they may already answer the question without needing a single
additional note.
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 · 148 lines · 94 tokens per session scan A f68481e992ac
knowledge-retrieval is a skill published in the GitHub repository JakubMikolajek/codex-skills-collection (5 stars, last pushed 7d ago), licensed MIT. It adds 94 tokens to every session and 1,841 once invoked, about $0.0005 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.