Context diff
Skill recallnet/codecontext/packages/claude-plugin/skills/context-diff
Force agents to read critical context left by other agents, enforced by linting and freshness checks.
npx -y skills add recallnet/codecontext --skill context-diffAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Check which @context annotations are affected by recent code changes. Use after editing code to verify context accuracy and flag stale annotations.
SKILL.md
0.8 KB, 120 tokens by cl100k_base, as published. Nobody here has run it
Run the codecontext diff command on the target file to see which annotations are affected by uncommitted changes.
npx codecontext --diff HEAD $ARGUMENTS
For each affected annotation:
- Check if the annotation still accurately describes the code.
- If accurate, recommend bumping
[verified:YYYY-MM-DD]to today's date. - If no longer accurate, recommend updating the annotation summary.
- If the annotated code was removed, recommend removing the annotation.
Flag any !critical annotations that changed — these require careful review.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most quality gates skills give in 120 tokens
Counted across 1,195 of the 2,094 authors here whose files we hold, read 2026-08-07
- Read the output and check the exit codein 54 of 1195, across 14 files
- Verify requirements using a line-by-line checklistin 53 of 1195, across 12 files
- Identify the verification command proving the claimin 51 of 1195, across 12 files
- Run the full verification commandin 50 of 1195, across 11 files
- Verify output confirms the claimin 49 of 1195, across 12 files
- Check version control diff after agent delegationin 46 of 1195, across 6 files
- State claim with evidencein 44 of 1195, across 4 files
- Run the test suitein 33 of 1195, across 26 files
- Keep state in memory by defaultin 27 of 1195, across 6 files
- Make prototype runnable with one commandin 26 of 1195, across 5 files
- Produce a verification reportin 25 of 1195, across 14 files
- Detect the package manager from lockfilesin 24 of 1195, across 5 files
Said here and by no other author read
- Run codecontext diff on the target file
- Check if affected annotations accurately describe code
- Recommend bumping verified date for accurate annotations
- Recommend updating inaccurate annotation summaries
- Recommend removing orphaned annotations
- Flag changed critical annotations for review
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.