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 hardiktiwari/PM-operating-OS --skill knowledge-updatergit clone --depth 1 https://github.com/hardiktiwari/PM-operating-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/hardiktiwari/pm-operating-os/knowledge-updater)<a href="https://agentmods.dev/skills/hardiktiwari/pm-operating-os/knowledge-updater"><img src="https://agentmods.dev/badge/skills/hardiktiwari/pm-operating-os/knowledge-updater/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/hardiktiwari/pm-operating-os/knowledge-updater"><img src="https://agentmods.dev/badge/skills/hardiktiwari/pm-operating-os/knowledge-updater.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 | $0.00043 | $0.00540 |
| Opus 5.5 | $0.00017 | $0.00216 |
| Sonnet 5.5 | $0.00009 | $0.00108 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
knowledge-updater 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Updater
Update knowledge layer documents (knowledge/) with automatic snapshotting. Before any update, the current version is saved to memory/knowledge-snapshots/ so the retrospective agent can track how strategy evolved over time.
When to Use
- Updating
knowledge/files (strategy, segments, metrics, competitive landscape) - After quarterly planning when strategy shifts
- After significant market or competitive changes
- When asked "update my strategy", "refresh knowledge docs", or "knowledge update"
Process
1. Identify What's Changing
Ask if not clear:
- Which knowledge doc(s) are being updated?
- What changed? (new strategy, updated segments, revised metrics, competitive shift)
- Why? (quarterly planning, market shift, exec direction, experiment results)
2. Snapshot Current State
Before making any changes, save the current version:
- Create a timestamped snapshot directory:
memory/knowledge-snapshots/YYYY-MM-DD/ - Copy the file(s) being updated into that directory with their original names
- Add a
_changelog.mdfile to the snapshot:
# Knowledge Snapshot — YYYY-MM-DD
**Reason for update:** [what triggered this change]
**Files updated:** [list]
## Changes Summary
- [File 1]: [what changed and why]
- [File 2]: [what changed and why]
3. Make the Update
Edit the knowledge file(s) in knowledge/{product}/ with the new content. Ensure:
- Format matches the existing template structure
- Changes are clearly reflected in the content
- No orphaned references (e.g., removing a segment that's referenced elsewhere)
4. Log as a Decision (optional)
If the knowledge update reflects a significant strategic shift, suggest logging it as a decision trace using the decision-logger skill.
Output
- Updated knowledge file(s) in
knowledge/{product}/ - Snapshot of previous version in
memory/knowledge-snapshots/YYYY-MM-DD/ - Changelog documenting what changed and why
Over time, snapshots enable:
- Drift detection: How has stated strategy evolved quarter over quarter?
- Decision coherence: Do knowledge updates align with decision traces?
- Retrospective analysis: The retrospective agent compares current knowledge to snapshots to surface gradual shifts
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 · 66 lines · 43 tokens per session scan A 786a7ba340cd
knowledge-updater is a skill published in the GitHub repository hardiktiwari/PM-operating-OS (5 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 540 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
docx
Create, read, edit, review, redline, comment on, merge, audit, render, and verify .docx Word documents, including layout-sensitive and OOXML-level work.
kayba-ace
This skill ships learnfromtraces.py, a script that reads OpenClaw session transcripts, feeds them through the ACE learning pipeline, and writes an updated skillbook to disk.
pptx
Create, inspect, edit, validate, render, and deliver PowerPoint presentations and templates while preserving OOXML structure and user metadata.
xlsx
Create, inspect, edit, recalculate, validate, render, and deliver Excel workbooks while preserving formulas, formatting, drawings, links, macros, and metadata.
Use when tasks involve reading, creating, or reviewing PDF files where rendering and layout matter; prefer visual checks by rendering pages (Poppler) and use Python tools such as reportlab, pdfplumber, and pypdf for generation and extraction.
save-md
Saves a named source to Markdown with provenance and faithful extraction through direct export endpoints. Use when asked to "save this article", "get the markdown", "transcribe this", or "keep this source". A URL supplied as task context alone does not trigger conversion; a chat summary stays in chat.