A question-answering workflow that first searches the br8n session knowledge base, then fills important gaps with web research. The session knowledge base is the information already collected for a repository and branch.

Use it for questions about information stored in the current repository session. It can answer from the knowledge base, research a narrow missing topic, or state when no project information is available.

It helps keep answers tied to what the current project already knows while still handling missing information. It also indicates when the available project knowledge is incomplete.

search — Skill for Claude Code by anthonysuherli

Install

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.

Any agent

npx skills add anthonysuherli/br8n --skill search

Clone the repo

git clone --depth 1 https://github.com/anthonysuherli/br8n

Made for: Claude Code.

Or install br8n, the plugin that ships this one along with the rest of its 11 skills, 3 hooks, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/anthonysuherli/br8n/search.svg)](https://agentmods.dev/skills/anthonysuherli/br8n/search)

Your own site

<a href="https://agentmods.dev/skills/anthonysuherli/br8n/search"><img src="https://agentmods.dev/badge/skills/anthonysuherli/br8n/search.svg" alt="Measured on agentmods" height="20"></a>

Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 495 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00077	$0.00495
Opus 5	$0.00039	$0.00247
Sonnet 5	$0.00015	$0.00099
Haiku 4.5	$0.00008	$0.00049

Measured 8d ago against content hash 33bb8c10775b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

search 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 8d 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.

skills/search/SKILL.md · 39 lines

What it actually says

br8n — Search

The primary verb. Answer the user's question from the session KB, and if the KB is thin on it, fill the gap online before answering. One skill, three moves: ground → grow → answer.

Step 1 — Ground

Follow ../_shared/preamble-first.md: resolve project/kb from git, then mcp__plugin_br8n_br8n__br8n_resume(project, kb, query=<the user's question>). Show the banner + resume card. Note the coverage band.

Step 2 — Grow (conditional)

Branch on coverage for the question:

rich → skip web research; the KB already covers it. Go to answer.
sparse → the KB partially covers it. Decide if the gap is material to a faithful answer. If yes, run a narrow /br8n:explore (see ../explore/SKILL.md) targeting only the thin slice; if no, answer from what's there and flag the soft spot.
gap → nothing to ground on. Either run mcp__plugin_br8n_br8n__br8n_explore(project, kb, prompt=<question>) to gap-fill (blocks 1–3 min, then re-tap), or, if the user wants a fast answer, say the KB is empty on this and answer from general knowledge with that caveat.

Only grow when the gap actually blocks a good answer — don't explore reflexively.

Step 3 — Answer

Answer the user's question from the assembled context (resume card + any fresh findings). Cite which findings/snapshots grounded the answer. If you explored, the new findings are already persisted — mention the next resume will be richer.

Changes

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.

8d ago First seen · 39 lines · 77 tokens per session scan A 33bb8c10775b

Subscribe to this mod's changes

search is a skill published in the GitHub repository anthonysuherli/br8n (1 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 495 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.

Claude Code Research context-engineering developer-tools knowledge-base mcp

search

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

br8n — Search

Step 1 — Ground

Step 2 — Grow (conditional)

Step 3 — Answer

What this file has done since we first saw it

Other skills, from other repositories

review

work

brainstorm

wish

report

quick