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/kochetkov-ma/claude-brewcode/semble-setupnpx skills add kochetkov-ma/claude-brewcode --skill semble-setupgit clone --depth 1 https://github.com/kochetkov-ma/claude-brewcodeWhat 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 | $0.00058 | $0.14975 |
| Opus 5 | $0.00029 | $0.07487 |
| Sonnet 5 | $0.00012 | $0.02995 |
| Haiku 4.5 | $0.00006 | $0.01498 |
Grade F, and why
semble-setup scanned grade F with 4 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
> `RC=3` is not a failure: a precondition is unmet (no `brew`) — print the manual fallback `curl -LsSf https://astral.sh/uv/install.sh | sh` **without running it**, and stop. Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
[ -n "$SD" ] || SD="$(find "$HOME/.claude/plugins/cache/claude-brewcode/brewcode" -maxdepth 3 -type d -path '*/skills/*' \( -name semble-setup -o -name semble \) 2>/dev/null | sort -V | tail -1)" Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
> **Stray cache root, installs that ran a pre-5.0.1 prefetch hook.** That hook spawned `semble search` without `SEMBLE_CACHE_LOCATION`, so the child used semble's own default root — `~/Library/Caches/semble` on macOS, `$ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> `RC=3` is not a failure: a precondition is unmet (no `brew`) — print the manual fallback `curl -LsSf https://astral.sh/uv/install.sh | sh` **without running it**, and stop. The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 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.
- assets/INSTALL.md 58 KB
- assets/semble-first.md.template 1.8 KB
- assets/semble-prefetch.mjs 30 KB runs code
- assets/semble-reminder.mjs 20 KB runs code
- assets/semble-session.mjs 7.4 KB runs code
- assets/semble-stats.mjs 11 KB runs code
- assets/semble-subagent.mjs 8.3 KB runs code
- assets/sembleignore.template 6.5 KB
- LICENSE 1.1 KB
- README.md 21 KB
- references/engine-landscape.md 58 KB
- references/hooks-roadmap.md 44 KB
- references/intent-routing.md 11 KB
- references/language-coverage.md 13 KB
- references/mcp-and-cache.md 12 KB
- references/output-contract.md 9.0 KB
- references/project-agent-migration.md 10 KB
- scripts/lib/semble-common.sh 27 KB runs code
- scripts/semble-agents.sh 24 KB runs code
- scripts/semble-cache.sh 12 KB runs code
- scripts/semble-guidance.sh 71 KB runs code
- scripts/semble-install.sh 16 KB runs code
- scripts/semble-mcp.sh 19 KB runs code
- scripts/semble-project.sh 45 KB runs code
- scripts/semble-remove.sh 19 KB runs code
- scripts/semble-state.sh 14 KB runs code
- scripts/semble-status.sh 44 KB runs code
- tests/fixtures/claude-json/absent.json 99 B
- tests/fixtures/claude-json/correct.json 363 B
- tests/fixtures/claude-json/duplicate.json 659 B
- tests/fixtures/claude-json/malformed.json 77 B
- tests/fixtures/claude-json/stale.json 326 B
- tests/fixtures/claude-json/upstream.json 238 B
- tests/fixtures/claude-json/wrongscope.json 395 B
- tests/fixtures/README.md 3.0 KB
- tests/fixtures/repo-a/build.gradle.kts 242 B
- tests/fixtures/repo-a/build.sh 333 B runs code
- tests/fixtures/repo-a/conf/application.properties 216 B
- tests/fixtures/repo-a/conf/deploy.groovy 305 B
- tests/fixtures/repo-a/conf/service.yaml 157 B
- tests/fixtures/repo-a/package.json 277 B
- tests/fixtures/repo-a/pyproject.toml 294 B
- tests/fixtures/repo-a/settings.gradle 173 B
- tests/fixtures/repo-a/src/auth_service.py 618 B runs code
- tests/fixtures/repo-a/src/Router.kt 363 B
- tests/fixtures/repo-a/src/session.ts 388 B runs code
- tests/fixtures/repo-a/src/TokenStore.java 469 B
- tests/fixtures/repo-a/web/index.html 340 B
- tests/fixtures/repo-a/web/LoginPanel.tsx 569 B
- tests/fixtures/repo-a/web/theme.css 301 B
- tests/fixtures/repo-b/config.yml 125 B
- tests/fixtures/repo-b/lib/metrics.ts 478 B runs code
- tests/fixtures/repo-b/lib/queue.py 497 B runs code
- tests/fixtures/repo-b/notes.md 290 B
- tests/fixtures/repo-b/run.sh 258 B runs code
- tests/fixtures/settings/empty.json 3 B
- tests/fixtures/settings/foreign.json 565 B
- tests/fixtures/settings/malformed.json 74 B
- tests/fixtures/settings/stale-path.json 882 B
- tests/run.sh 3.1 KB runs code
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.
- 3d ago First seen · 634 lines · 58 tokens per session scan F 10ba0e1b8899
semble-setup is a skill published in the GitHub repository kochetkov-ma/claude-brewcode (31 stars, last pushed 5d ago), with no licence file. It adds 58 tokens to every session and 14,975 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it F with 4 findings (downloads and executes remote code, reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
golden-rss
Use when testing the rss golden build.
omh-buzz
This is a Hermes-native buzz workflow skill.
omh-code-review
This is a Hermes-native code-review workflow skill.
redteam-api-detail-pack
Domain routing and boundary guidance for authorized API security testing, including BOLA/IDOR, authentication bypass, mass assignment, missing rate limits, and GraphQL issues. Use when a task belongs to the API testing domain and needs scope, evidence, pivot, or exit criteria.
redteam-postex-detail-pack
Domain routing and boundary guidance for authorized post-exploitation testing after initial access, including privilege escalation, persistence, lateral movement, data collection, and cleanup considerations. Use when a task belongs to the post-exploitation domain and needs scope, evidence, pivot, or exit criteria.