Mechanism: Completion Bias — When “Done” Means the Agent Stopped Talking
Completion bias is treating the agent's last message — confident summary, "all tests pass," task complete — as proof of…
Mechanism: Vibe Drift — When the Goal Mutates Mid-Session
Vibe drift is the anti-pattern where the original (/mechanism-goal/) silently changes mid-session — through follow-up requests, agent suggestions, or scope…
Mechanism: PR-Sized Vibes — Match Sessions to Reviewable Diffs
PR-sized vibes means sizing each agent session so its output fits a reviewable pull request — diff a human can…
Mechanism: MCP Tool Bridge — Structured Access to the Outside World
An MCP tool bridge gives the agent structured, scoped access to external systems — browser, database, APIs, docs — through…
Mechanism: Mode Switching — Plan, Build, and Debug Are Different Jobs
Mode switching is deliberately changing cognitive mode — plan, implement, debug, ask-only — so the agent (and you) do one…
Mechanism: Hooks & Automation — Trigger Agents on Events
Hooks and automation connect agent work to events — save, commit, PR open, CI fail — so (/mechanism-verify-loop/) and fix…
Mechanism: Best-of-N — Run Multiple Approaches, Pick the Winner
Best-of-N is running N independent agent attempts on the same goal — separate branches, chats, or models — then choosing…
Mechanism: Branch-per-Experiment — Isolate Each Vibe
Branch-per-experiment means each agent attempt, slice, or hypothesis gets its own git branch — so you can compare, abandon, or…
Mechanism: Playground — Experiment Without Breaking Production
A playground is an isolated environment — branch, directory, sandbox repo, or local-only config — where agent experiments cannot damage…
Mechanism: Diff-as-Context — Steer Attention to What Changed
Diff-as-context is using the actual change set — `git diff`, PR patch, or rejected hunks — as the primary steering…