Mechanism: Pair Vibe — Human Steers, Agent Executes
Pair vibe is two-role collaboration: the human steers direction, goals, and checkpoints while the agent executes edits and commands —…
Mechanism: Confidence Calibration — When to Trust vs Re-Read Every Line
Confidence calibration is matching how much you trust agent output — skim, standard review, line-by-line audit — to risk, novelty,…
Mechanism: Over-Automation Trap — Loops That Amplify Bad Assumptions
The over-automation trap is automating agent (/mechanism-loop/) or (/mechanism-hooks/) without strong (/mechanism-goal/), (/mechanism-verify-loop/), and (/mechanism-termination-condition/) — so wrong assumptions get…
Mechanism: Stuck Detection — Same Error N Times, Change Strategy
Stuck detection is recognizing when the same failure repeats across N agent passes — same test, same error, same wrong…
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…