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 lesliebiubiubiu/agent-context-kb-skill --skill agent-context-kbgit clone --depth 1 https://github.com/lesliebiubiubiu/agent-context-kb-skillWrote 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/lesliebiubiubiu/agent-context-kb-skill/agent-context-kb)<a href="https://agentmods.dev/skills/lesliebiubiubiu/agent-context-kb-skill/agent-context-kb"><img src="https://agentmods.dev/badge/skills/lesliebiubiubiu/agent-context-kb-skill/agent-context-kb/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/lesliebiubiubiu/agent-context-kb-skill/agent-context-kb"><img src="https://agentmods.dev/badge/skills/lesliebiubiubiu/agent-context-kb-skill/agent-context-kb.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 | $0.00086 | $0.01045 |
| Opus 5 | $0.00043 | $0.00522 |
| Sonnet 5 | $0.00017 | $0.00209 |
| Haiku 4.5 | $0.00009 | $0.00104 |
Grade A, and why
agent-context-kb 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 10d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent KB
Use this skill to manage a repository-local .agent-kb/ for coding agents. The
KB is an agent-facing index of durable project knowledge, not a replacement for
human docs.
Quick Start
Run the bundled script from the skill directory. Use --root . in the target repo.
python3 scripts/agent_kb.py init --root /path/to/repo
python3 scripts/agent_kb.py upgrade --root /path/to/repo
python3 scripts/agent_kb.py validate --root /path/to/repo
python3 scripts/agent_kb.py note --root /path/to/repo --title "Auth session note" --target decisions/active/auth-storage.md --body "Durable fact."
python3 scripts/agent_kb.py compile --root /path/to/repo
python3 scripts/agent_kb.py trim --root /path/to/repo
python3 scripts/agent_kb.py trim --root /path/to/repo --write
python3 scripts/agent_kb.py stats --root /path/to/repo
Workflow
init: create the scaffold and runtime protocol. Default versioning is a personal nested.agent-kb/.git; use--sharedor--localwhen requested. When init reports an empty scaffold, initialization completes only after you have offered the user the one-time distillation pass described in the init output — then run it if they accept, or leave the scaffold as-is if they decline.upgrade: refresh generated protocol/scaffold files conservatively.validate: run after KB edits; fix errors before finishing.note: capture durable knowledge when the stable target is unclear.compile: merge inbox notes with validSuggested targetfiles.trim: run it and follow its output. Size is a proxy; compact redundant or stale information, and stop when the remaining content is genuinely non-redundant. Usetrim --writeonly for deterministic cleanup.stats: run it with no flags unless the user asked for one, then do what its output says — it states its own options. Paste the full output verbatim in a fenced code block; the ASCII charts are the deliverable.
Knowledge Rules
Record durable knowledge only; the full do/don't canon lives in the generated
.agent-kb/start.md. Summarize or link human docs rather than copying them in.
What ships with it
3 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.
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.
- 10d ago First seen · 98 lines · 86 tokens per session scan A fea3dea29f19
agent-context-kb is a skill published in the GitHub repository lesliebiubiubiu/agent-context-kb-skill (7 stars, last pushed 25d ago), licensed MIT. It adds 86 tokens to every session and 1,045 once invoked, about $0.0004 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
memorybox
Diagnoses bloated MEMORY.md files, splits oversized sections into domain-specific files, archives stale daily logs, and deduplicates content using a 3-tier hierarchy (MEMORY.md → domains/ → archive/). Use when MEMORY.md exceeds 10KB, context pressure is high, or the user asks to clean up, organize, or maintain agent…
openclaw-memorybox
Memory health CLI that diagnoses bloated MEMORY.md files, splits oversized sections into domain files, archives stale daily logs, and runs continuous health monitoring. Use when MEMORY.md exceeds 10KB, context windows overflow from memory bloat, or agent sessions slow down from loading large memory files. Pure bash…
wiki-import
Import a wiki knowledge graph into the current vault — either from a graph.json export file (stubs) or from an OKF (Open Knowledge Format) markdown bundle (full page bodies). Use this skill when the user says "import wiki", "import from export", "load graph.json", "import vault", "import OKF bundle", "import OKF"…
hermes-history-ingest
Ingest Hermes agent history into the Obsidian wiki. Use this skill when the user wants to mine their past Hermes sessions for knowledge, import their /.hermes folder, extract insights from previous Hermes conversations, or says things like "process my Hermes history", "add my Hermes memories to the wiki", "ingest…
wiki-narrate
Turn a wiki topic into a cited Markdown briefing, plain-language explanation, or progressive lecture. Use this skill for topic-based briefing, explanation, and lecture requests that must stay within the evidence compiled in an Obsidian vault.
session-brain
Build and maintain a topic graph over your agent session history. Reads every Claude session transcript plus the pruned sessions that survive only in history.jsonl, clusters them by topic using local TF-IDF (no API calls, no embeddings), and writes an interactive graph you can open in a browser. Use when the user says…