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 agentmods add skills/kelp/agent-plugins/kb-research-policynpx skills add kelp/agent-plugins --skill kb-research-policygit clone --depth 1 https://github.com/kelp/agent-pluginsWrote 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/kelp/agent-plugins/kb-research-policy)<a href="https://agentmods.dev/skills/kelp/agent-plugins/kb-research-policy"><img src="https://agentmods.dev/badge/skills/kelp/agent-plugins/kb-research-policy.svg" alt="Measured on agentmods" 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 | $0.00167 | $0.01437 |
| Opus 5 | $0.00084 | $0.00718 |
| Sonnet 5 | $0.00033 | $0.00287 |
| Haiku 4.5 | $0.00017 | $0.00144 |
Grade A, and why
kb-research-policy 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 4d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KB Research Policy
Travis maintains a three-layer personal knowledge base. This skill tells you how to find things in it efficiently from any session, regardless of your current working directory.
The three layers:
raw/— immutable source archive (web crawls, PDFs, snapshots). Never edit.wiki/— synthesized notes in buckets:sources/,concepts/,reports/,questions/,projects/,playbooks/,dependencies/.index/— cheap one-line-per-entry routing files. Read these first.
For edge cases not covered here, read <kb>/CLAUDE.md
and <kb>/AGENTS.md directly.
Step 1: Resolve the KB path
Run ${CLAUDE_PLUGIN_ROOT}/scripts/resolve-kb-path.sh and
capture its stdout as kb_path. Every subsequent command
uses "$kb_path" (double-quoted).
kb_path=$(bash "${CLAUDE_PLUGIN_ROOT}/scripts/resolve-kb-path.sh")
If the script exits non-zero, relay its stderr message to the user verbatim and stop — do not guess a fallback path.
Step 2: Read the index first
Index files are small (one line per entry) and are the cheapest first hop. Read only the ones relevant to the question. Do not open full wiki notes yet.
Current index files under <kb>/index/:
sources.md— web pages and docs Travis has readconcepts.md— synthesized topic pagesopen-questions.md— unresolved inquiriesplaybooks.md— reusable how-to notesprojects.md— project overviewsdependencies.md— external tools and librariesdoc-packs.md— downloaded external doc packs (AUTO-GENERATED)freshness.md— last updated_at per external source (AUTO-GENERATED)authoritative-files.md— canonical file references
If a listed index file does not exist, skip it silently. Not every KB populates every bucket.
After reading the relevant index files, you should have a shortlist of candidate note IDs. If the index alone gives a confident, complete answer, you may skip Step 3 and answer directly. Otherwise proceed to Step 3 — the hand-maintained index can lag actual note content, so a thin or stale-looking index entry is not itself a complete answer.
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.
- 4d ago First seen · 187 lines · 167 tokens per session scan A 58721363bb01
kb-research-policy is a skill published in the GitHub repository kelp/agent-plugins (2 stars, last pushed today), licensed MIT. It adds 167 tokens to every session and 1,437 once invoked, about $0.0008 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
cdb-scan
Map this codebase into project memory — a code graph of every symbol and how they connect, plus a written profile of stack, layout, conventions and workflows. Re-run any time to refresh both in place. Use when memory is newly installed on an existing project, or when the project has changed enough that the stored map…
ctx-purge
Purge the context-mode knowledge base. Permanently deletes all indexed content and resets session stats. This is destructive and cannot be undone. Trigger: /context-mode:ctx-purge.
ctx-index
Index a local file or directory into context-mode's persistent FTS5 knowledge base so future ctxsearch calls can retrieve focused snippets without rereading raw files. Trigger: /context-mode:ctx-index.
ctx-search
Search context-mode's persistent FTS5 knowledge base for previously indexed local project content, documentation, or session memory. Trigger: /context-mode:ctx-search.
ctx-stats
Show how much context window context-mode saved this session. Displays token consumption, context savings ratio, and per-tool breakdown. Read-only — shows stats only, no reset capability. To wipe the knowledge base entirely, use ctxpurge instead. Trigger: /context-mode:ctx-stats.
autolearn
Compound a solved problem into a durable in-repo learning doc. Use when a verified non-trivial fix lands, the user says "compound this", "document this fix", or "remember this". This is the automatic-capture entry point; for an explicitly requested one-off write-up, use compound.