docs(hooks): add "reading the full output" to agent instructions#2156
Open
tiagodocouto wants to merge 1 commit into
Open
docs(hooks): add "reading the full output" to agent instructions#2156tiagodocouto wants to merge 1 commit into
tiagodocouto wants to merge 1 commit into
Conversation
Agent instruction files explained how to run commands through rtk but not how to recover the complete, unfiltered output when the filtered summary is not enough (e.g. to confirm a test or build claim). Add a short "Reading the full output" section to every agent template, pointing to `rtk proxy <cmd>` and the `[full output: <path>]` tee log. The Claude template also swaps its dangling "Refer to CLAUDE.md" line for `rtk --help`.
|
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
hooks/*/rtk-awareness.mdandrules.md). The templates tell agents to run commands throughrtk, but not how to recover the complete, unfiltered output when the filtered summary isn't enough — e.g. to confirm a "tests pass" / "build clean" claim rather than skim it. Both raw paths already exist (rtk proxy <cmd>and the[full output: <path>]tee log) but weren't documented where agents actually read. Mirrors the principle already inCONTRIBUTING.md(respect explicitly-requested detail).Refer to CLAUDE.mdline withrtk --help.Test plan
cargo fmt --all && cargo clippy --all-targets && cargo test— fmt clean, test 1974 passed, 0 failed. (clippy hits a pre-existinguninlined_format_argslint inbuild.rs, untouched by this docs-only diff; CI is green ondevelop.)rtk cargo test(filtered) vsrtk proxy cargo test(raw) vs the[full output: <path>]tee log against a failing and a non-compiling crate — the documented behavior matches.