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 bhaumikmaan/claude-code-master-skills --skill knowledge-managementgit clone --depth 1 https://github.com/bhaumikmaan/claude-code-master-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/bhaumikmaan/claude-code-master-skills/knowledge-management)<a href="https://agentmods.dev/skills/bhaumikmaan/claude-code-master-skills/knowledge-management"><img src="https://agentmods.dev/badge/skills/bhaumikmaan/claude-code-master-skills/knowledge-management/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/bhaumikmaan/claude-code-master-skills/knowledge-management"><img src="https://agentmods.dev/badge/skills/bhaumikmaan/claude-code-master-skills/knowledge-management.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 | $0.00056 | $0.01530 |
| Opus 5.5 | $0.00022 | $0.00612 |
| Sonnet 5.5 | $0.00011 | $0.00306 |
| Haiku 4.5 | $0.00006 | $0.00153 |
Grade A, and why
knowledge-management 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 2mo 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Management
CRITICAL: Memory is for knowledge NOT derivable from the current project state. If you can grep for it or read it from CLAUDE.md, don't save it as memory.
Memory Taxonomy
Four types of knowledge, each with distinct purpose and storage rules:
user — Who the user is, their role, expertise, preferences, and how to tailor your work to them.
- Save when: You learn about the user's role, knowledge level, or working style.
- Use when: Tailoring explanations, calibrating technical depth, adjusting communication style.
- Example: "Deep Go expertise, new to React — frame frontend explanations in terms of backend analogues."
feedback — Guidance on how to approach work. Both corrections ("don't do X") AND confirmations ("yes, keep doing that").
- Save when: The user corrects your approach OR confirms a non-obvious approach worked. Corrections are easy to spot; confirmations are quieter — watch for them.
- Use when: Guiding behavior so the user doesn't repeat the same guidance.
- Structure: Lead with the rule, then Why: (reason/incident), then How to apply: (when this kicks in).
- Example: "Integration tests must hit a real database. Why: mock/prod divergence masked a broken migration. How to apply: any test that touches DB queries."
project — Ongoing work, goals, initiatives, and decisions NOT derivable from code or git history.
- Save when: You learn who is doing what, why, or by when. Convert relative dates to absolute dates ("Thursday" → "2026-04-03").
- Use when: Understanding context behind requests, anticipating coordination issues.
- Structure: Lead with the fact/decision, then Why: and How to apply:.
- Example: "Merge freeze begins 2026-04-05 for mobile release cut. Flag non-critical PR work after that date."
reference — Pointers to where information lives in external systems.
- Save when: You learn about resources outside the project directory and their purpose.
- Use when: The user references an external system or asks about external resources.
- Example: "Pipeline bugs tracked in Linear project 'INGEST'."
What ships with it
1 file 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.
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.
- 2mo ago First seen · 142 lines · 56 tokens per session scan A 227fb7007bb3
knowledge-management is a skill published in the GitHub repository bhaumikmaan/claude-code-master-skills (3 stars, last pushed 7mo ago), licensed MIT. It adds 56 tokens to every session and 1,530 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
chief-of-staff
A long-running coordination role that uses subagents, recurring schedules, and a linked folder of Markdown notes called a wiki. The wiki preserves decisions, problems, preferences, and other knowledge between sessions.
cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops.
ralph-memory
Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations.
harness-memory-maintenance
Audit and maintain harness memory through reviewed aiwg memory plans, with owner receipts, verification and recovery.
distill-feedback
A process for turning corrections you give an agent into lasting working rules. It reviews saved conversations and asks for approval before changing those rules.
session-explore
Investigate past AI session activity with cited catalog search, timelines, tool analytics, and bounded comparisons across providers.