Cut the 'it's user-invoked' rationale from the five preconditions

Per writing-for-agents' no-op test: "tell the user to run /X" is
already an unambiguous instruction with no branch where the agent
would otherwise try to call it, so the trailing justification changes
nothing at runtime. It also duplicates the rule .agents/invocation.md
already states as the single source of truth. Cut it from all five
call sites; the carve-out paragraph there is the one place the reason
needs to live.
This commit is contained in:
Remote Box Agent
2026-08-15 21:22:05 +00:00
parent 1dab98299c
commit 6a34259e99
5 changed files with 5 additions and 5 deletions
+1 -1
View File
@@ -10,7 +10,7 @@ Two-axis review of the diff between `HEAD` and a fixed point the user supplies:
Both axes run as **parallel sub-agents** so they don't pollute each other's context, then this skill aggregates their findings.
The issue tracker should have been provided to you. If `docs/agents/issue-tracker.md` is missing, tell the user to run `/setup-matt-pocock-skills` — it's user-invoked, so you can't call it yourself.
The issue tracker should have been provided to you. If `docs/agents/issue-tracker.md` is missing, tell the user to run `/setup-matt-pocock-skills`.
## Process