When things go wrong
- 01Loops, polluted context and restarting10 min
The sign of a loop is the same failure message repeating, a saturated context is handled by a targeted compaction or a full clear, and starting over with a hand written summary of the decisions already made beats insisting inside a degraded conversation.
- 02Undoing and recovering a change9 min
To undo Claude Code's last action within the current session, the checkpoint menu opened by /rewind now comes before Git, which remains necessary for everything this system does not track: a change made by a bash command, a sub-agent's background edit, or a file linked by a symbolic or hard link.
- 03API errors and rate limits9 min
A call to the API can fail in several different ways: a 400 or 404 error most often signals a malformed request that must be corrected before any retry, except for the special case of a 400 returned for a spending cap that has been reached, whereas a 429 error only resolves itself by waiting if it carries a Retry-After header, which is not the case for a spending cap that has been reached.
- 04A stuck command7 min
A shell command that stops responding is cut off with Ctrl+C without closing the session, and the delay that switches it to a background task is already fixed by Claude itself, not by a prefix you add by hand.
- 05Several sessions die together, suspect the machine9 min
When several sessions die at the same instant with no trace whatsoever in their own logs, the likely cause is the operating system killing processes under memory pressure, and the system log settles the question faster than a hunt through application errors.
- 06The request may rest on a false premise9 min
A request can describe the symptom accurately while getting the cause wrong, and carrying out that request to the letter then fixes nothing, or makes the situation worse.
- 07Read the function called next, prove the culprit10 min
A fix whose unit test goes green can be undone, within the same execution turn, by the function called right after it, and the already fixed function only becomes a proven culprit once a test has isolated its effect from that of the functions that follow.