I created Nitro Skills to reduce token usage of my Claude agents

Dextrata released Nitro Skills, an open-source toolkit of 15 skills that reduces token usage for Claude agents by keeping each skill's logic in an executed script rather than in the model's context. Each skill is a short SKILL.md file plus a script, and the package requires only Python 3, installing into the global Claude directory and wiring up supporting hooks automatically via a git clone of the Dextrata/nitro-skills repository followed by python install.py. The skills include hashpatch for editing files through hashed line anchors, rerun for caching test, build, and lint output, and budget for tracking token spend per command and blocking unbounded floods.

Each skill is a short SKILL.md — the only part that ever enters the model's context — plus a script that gets executed, never read. The clever logic costs zero tokens no matter how many times it's reused. The first three shrink reads, edits and repeated command output. The rest attack everything else: repeated output, long strings, reassurance reads, mechanical edits, logs, payloads, traces, diffs, search hops, re-derived facts, and unbounded floods. hashpatch Edit files by pointing at hashed line anchors instead of quoting whole files. rerun Cache and reuse output from tests, builds, and lints across repeat runs. probe Inspect a module's API by running it, not by reading its source. seen Fold already-shown output blocks into one-line pointers. alias Shorten long repeated strings hashes, UUIDs, paths into small tokens. believe Verify a claim about a file against reality without re-reading it. refactor Describe a mechanical multi-file edit in a sentence instead of a diff. mine Cluster huge logs into a handful of templated lines with counts. shape Print the schema of structured data instead of dumping the payload. trace Strip library noise from stack traces down to the user-code frames. sdiff Summarize a diff by symbol instead of printing every changed line. q Answer structural code questions from a cached symbol index. blast Show a symbol's callers and callees before you change its signature. recall Persist answers to "where/how is X handled" across sessions. budget Track token spend per command and block unbounded floods. Requires only Python 3. Installs into your global Claude directory and wires up the supporting hooks automatically. git clone https://github.com/Dextrata/nitro-skills.git cd nitro-skills python install.py See the full README https://github.com/Dextrata/nitro-skills readme for manual install, flags, and a CLAUDE.md example that makes usage legible to the agent.