Lcc — Development skill for Claude Code
Compact coding-agent context without summarizing it away.
How to install Lcc
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open lucasmartins-ai/lcc and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Lcc does
Compact coding-agent context without summarizing it away. Verbatim, offline, with a receipt and recall for every cut. CLI, MCP server, Claude Code plugin. MIT.
Alternatives in Development
- Arrecall — AgentRecall on-demand recall — surface past fixes, decisions, and patterns mid-session without leaving your fl 370 ★
- Bm Scan — Build or refresh the basemind index by running basemind scan via the CLI — works without the MCP server (use i 94 ★
- Analysis — You are summarizing Linux command output for an operator in a terminal 55 ★
README
lcc — Local Context Compiler
**Compact coding-agent context without summarizing it away.**
lcc cuts what the model does not need, keeps everything else byte for byte, and writes a receipt.
[](https://pypi.org/project/local-context-compiler/) [](https://pypi.org/project/local-context-compiler/) [](https://github.com/lucasmartins-ai/lcc/actions/workflows/ci.yml) [](LICENSE) [](https://github.com/lucasmartins-ai/lcc/stargazers)
`/compact` vs lcc
Claude Code's `/compact` replaces your session with a summary written by a model. Summaries drop the exact error, path or line the agent needs two turns later. lcc does the opposite: old tool outputs leave the context but stay one `recall` away, and every user and assistant message is kept as it was.
| One real Claude Code session (193 messages, 75 tool calls) | tokens | user and assistant messages | removed tool outputs |
|---|---|---|---|
| before | 57,083 | 43, as written | — |
/compact |
one summary | rewritten into the summary | gone |
lcc (rules, stashed) |
28,807 (−49.5%) | 43 / 43 byte for byte | 33, each one recall away |
Measured with `lcc measure-session` (1.2.0, offline, exact `o200k_base` token count). That session is one of the best cases. **Across all 266 of my long se
Related Skills
Claude Compact Keeper
Compaction without amnesia: the summarizer is told to keep your goal, constraints, decisions and paths verbati
Verify Chain
Verify the full receipt chain offline — structure (single unbroken chain from GENESIS, content hashes) and eve
Claudecut
Run Claude Code with almost everything cut away: one shell tool, a 36-token system prompt, and a capped contex
V Memory Refresh
(Re)index docs/superpowers prose into the local V-memory cache so recall is current. Incremental by file hash;
Longhand
Lossless local memory for Claude Code. The full, unabbreviated version. Every tool call, every file edit, ever
Archive Transcript
Archive a podcast/talk transcript from a URL into the vault — verbatim body plus a synthesis header — without
Related Agents
Frame Inspector
Inspects Shorts Studio frame sheets (analysis overviews, candidate previews, QA contact/cut sheets) and return
Legal Playbook Checker
Compares every clause in a clause map against the per-document-type playbook YAML (market position, red flags,
Mer Recall
Worker that loads a project's Memory v2 context (mem_state, mem_context, mem_search, mem_get) and reconciles i
