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 squadcodercom/squadcoder --skill sc-codebase-indexgit clone --depth 1 https://github.com/squadcodercom/squadcoderWrote 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/squadcodercom/squadcoder/sc-codebase-index)<a href="https://agentmods.dev/skills/squadcodercom/squadcoder/sc-codebase-index"><img src="https://agentmods.dev/badge/skills/squadcodercom/squadcoder/sc-codebase-index/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/squadcodercom/squadcoder/sc-codebase-index"><img src="https://agentmods.dev/badge/skills/squadcodercom/squadcoder/sc-codebase-index.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 | $0.00136 | $0.00749 |
| Opus 5.5 | $0.00054 | $0.00300 |
| Sonnet 5.5 | $0.00027 | $0.00150 |
| Haiku 4.5 | $0.00014 | $0.00075 |
Grade A, and why
sc:codebase-index 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 1mo 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase indexing & semantic search (reuse the code-memory MCP)
SquadCoder ships the code-memory MCP (local, offline, no API key — uvx code-memory) for
Cursor-style semantic code search. This skill tells you when and how to use it so the agent indexes
and searches the codebase the way a Cursor user expects — without anyone wiring it by hand.
If the
code-memorytools (index_codebase,search_code,search_docs,search_history) are not available, the MCP is disabled — fall back togrep/globand (optionally) tell the user they can enable code-memory in Settings ▸ MCP for semantic search. Do not invent these tools.
When to use semantic search vs grep
- Conceptual / fuzzy ("where is rate-limiting handled?", "find everything about billing", "how does
auth flow work?") → semantic (
search_code/search_docs). It finds relevant code even when the wording differs from the symbols. - Exact token (a known symbol, string literal, error code, file name) →
grep/glob. Don't pay for embeddings when you already know the literal. - History / "who changed this and why" →
search_history(commit/blame/file-history).
Flow
- Index once per workspace. On the first semantic query in a session (or when the user opens a new /
large codebase), call
index_codebasefor the project root. It's incremental — re-running is cheap and keeps the index fresh after edits. The first ever run downloads the embedding model (~600 MB) and may take a minute; say so if the user is waiting. - Search. Use
search_code(andsearch_docsfor prose/markdown) with a natural-language query. Pull the top hits. - ALWAYS verify before acting. Semantic hits are leads, not ground truth — open the actual files and read the real lines before you edit, quote, or conclude. Never edit a file you only saw in a search snippet.
- Keep it fresh. After a batch of edits that change structure, re-index so later searches stay accurate.
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.
- 1mo ago First seen · 48 lines · 136 tokens per session scan A 19318ba8336f
sc:codebase-index is a skill published in the GitHub repository squadcodercom/squadcoder (12 stars, last pushed 3mo ago), licensed MIT. It adds 136 tokens to every session and 749 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
test-fix
Diagnose and minimally fix a failing test, then re-run.
hatch3r-incident-response
Handles production incidents with structured triage, mitigation, and post-mortem. Use when responding to production issues, outages, or security incidents.
hatch3r-bug-fix
Step-by-step bug fix workflow. Diagnose root cause, implement minimal fix, write regression test. Use when fixing bugs, working on bug report issues, or when the user mentions a bug.
hatch3r-perf-audit
Profiles and optimizes application performance against defined budgets. Use when investigating performance issues, auditing performance budgets, or optimizing hot paths.
hatch3r-logical-refactor
Workflow for changing behavior or logic flow without adding new features or overhauling UI. Use when modifying business logic, data flows, behavioral rules, or working on logical refactor issues.
grade-and-fix-daedalus
How to grade a Daedalus run (or pasted agent transcript), root-cause the failure, and ship the fix to Daedalus CORE as a stacked PR — without modifying the prompt-vault sandbox (read-only grading). Covers recurring bug archetypes (Unicode punctuation patch mismatch, syntax-vs-type mislabel, emoji box misalignment…