update skills

.agents/skills/diagnosing-bugs/SKILL.md

@@ -1,140 +1,40 @@
 ---
 name: diagnosing-bugs
-description: Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
+description: Investigate bugs and performance regressions to explain their cause with evidence. Use for diagnosis or debugging; implement repairs only when fixing is also requested.
 ---
 
 # Diagnosing Bugs
 
-A discipline for hard bugs. Skip phases only when explicitly justified.
+Read the relevant flow, existing tests, `CONTEXT.md`, and applicable ADRs. Establish the requested outcome: diagnosis ends with a cause and evidence; an authorized fix also includes repair and regression checks. Keep all investigation within permitted systems and preserve unrelated work.
 
-When exploring the codebase, read `CONTEXT.md` (if it exists) to get a clear mental model of the relevant modules, and check ADRs in the area you're touching.
+## Find a useful signal
 
-## Redact
+Start from the reported symptom and what is already known. Read code, logs, and recent changes to form hypotheses; do not require a running reproduction before inspecting the code.
 
-This skill has you show commands, outputs and captured artifacts. **Redact every secret first** — write `<REDACTED>` in its place. Build loops against env vars, so the credential stays in the environment rather than in what you show. Captured artifacts carry auth headers: quote only the lines that carry the signal.
+Prefer the smallest reliable reproduction: an existing failing test, a scoped command with dummy input, a local request, or a browser check. Choose a harness only if existing checks cannot reach the failure. When a human must perform the trigger, adapt [the HITL loop template](scripts/hitl-loop.template.sh); do not run it unattended.
 
-If the redacted output is not enough to diagnose the bug, say so and ask the user.
+Capture the exact error, wrong result, or measured regression. Distinguish the reported bug from nearby failures. Minimize inputs when it helps separate causes; perfect minimization and second-long execution are not prerequisites.
 
-## Phase 1 — Build a feedback loop
+For intermittent bugs, record attempts, failures, and environmental conditions. Use bounded stress or repeated runs when safe; do not overload shared systems. A low reproduction rate is evidence, not a reason to abandon inspection.
 
-**This is the skill.** Everything else is mechanical. If you have a **tight** pass/fail signal for the bug — one that goes red on _this_ bug — you will find the cause; bisection, hypothesis-testing, and instrumentation all just consume it. If you don't have one, no amount of staring at code will save you.
+If execution is unavailable, continue safe code/trace analysis, distinguish a probable cause from a confirmed one, and state what would confirm it. Request only the missing artifact or access that materially limits progress. Production instrumentation requires explicit authority.
 
-Spend disproportionate effort here. **Be aggressive. Be creative. Refuse to give up.**
+## Test explanations
 
-### Ways to construct one — try them in roughly this order
+Rank plausible hypotheses by evidence and state a prediction for each. One well-supported explanation may be enough; compare alternatives when uncertainty warrants it.
 
-1. **Failing test** at whatever seam reaches the bug — unit, integration, e2e.
-2. **Curl / HTTP script** against a running dev server.
-3. **CLI invocation** with a fixture input, diffing stdout against a known-good snapshot.
-4. **Headless browser script** (Playwright / Puppeteer) — drives the UI, asserts on DOM/console/network.
-5. **Replay a captured trace.** Save a real network request / payload / event log to disk; replay it through the code path in isolation.
-6. **Throwaway harness.** Spin up a minimal subset of the system (one service, mocked deps) that exercises the bug code path with a single function call.
-7. **Property / fuzz loop.** If the bug is "sometimes wrong output", run 1000 random inputs and look for the failure mode.
-8. **Bisection harness.** If the bug appeared between two known states (commit, dataset, version), automate "boot at state X, check, repeat" so you can `git bisect run` it.
-9. **Differential loop.** Run the same input through old-version vs new-version (or two configs) and diff outputs.
-10. **HITL bash script.** Last resort. If a human must click, drive _them_ with `scripts/hitl-loop.template.sh` so the loop is still structured. Captured output feeds back to you.
+Use targeted inspection or probes to distinguish predictions. Change one relevant variable at a time where practical. Tag temporary instrumentation with a task-unique prefix, avoid sensitive payloads, and keep track of exactly what you added.
 
-Build the right feedback loop, and the bug is 90% fixed.
+For performance, measure the same workload against a baseline before proposing an optimization; account for warmup and noise. Use profiling, query plans, or bisection when they help isolate the cause. Keep bisection out of a shared dirty worktree.
 
-### Tighten the loop
+## Repair only when requested
 
-Treat the loop as a product. Once you have _a_ loop, **tighten** it:
+For an authorized fix, turn the reproduction into a regression check before the repair where feasible. Exercise the real failing caller pattern: a single-caller unit test cannot prove a multi-caller race is fixed.
 
-- Can I make it faster? (Cache setup, skip unrelated init, narrow the test scope.)
-- Can I make the signal sharper? (Assert on the specific symptom, not "didn't crash".)
-- Can I make it more deterministic? (Pin time, seed RNG, isolate filesystem, freeze network.)
+Apply the smallest root-cause correction, rerun the original scenario, then relevant surrounding tests. If no reliable check is available, state the resulting verification gap rather than claiming success from an unrelated green test.
 
-A 30-second flaky loop is barely better than no loop; a 2-second deterministic one is tight — a debugging superpower.
+## Hand off
 
-### Non-deterministic bugs
+Remove only your own temporary probes and disposable artifacts. Report the cause, supporting evidence, checks run, and remaining uncertainty. For a fix, also report the changed behavior and regression result.
 
-The goal is not a clean repro but a **higher reproduction rate**. Loop the trigger 100×, parallelise, add stress, narrow timing windows, inject sleeps. A 50%-flake bug is debuggable; 1% is not — keep raising the rate until it's debuggable.
-
-### When you genuinely cannot build a loop
-
-Stop and say so explicitly. List what you tried. Ask the user for: (a) access to whatever environment reproduces it, (b) a redacted captured artifact (HAR file, log dump, core dump, screen recording with timestamps), or (c) permission to add temporary production instrumentation. Do **not** proceed to hypothesise without a loop.
-
-### Completion criterion — a tight loop that goes red
-
-Phase 1 is done when the loop is **tight** and **red-capable**: you can name **one command** — a script path, a test invocation, a curl — that you have **already run at least once** (show the invocation and its output, redacted), and that is:
-
-- [ ] **Red-capable** — it drives the actual bug code path and asserts the **user's exact symptom**, so it can go red on this bug and green once fixed. Not "runs without erroring" — it must be able to _catch this specific bug_.
-- [ ] **Deterministic** — same verdict every run (flaky bugs: a pinned, high reproduction rate, per above).
-- [ ] **Fast** — seconds, not minutes.
-- [ ] **Agent-runnable** — you can run it unattended; a human in the loop only via `scripts/hitl-loop.template.sh`.
-
-If you catch yourself reading code to build a theory before this command exists, **stop — jumping straight to a hypothesis is the exact failure this skill prevents.** No red-capable command, no Phase 2.
-
-## Phase 2 — Reproduce + minimise
-
-Run the loop. Watch it go red — the bug appears.
-
-Confirm:
-
-- [ ] The loop produces the failure mode the **user** described — not a different failure that happens to be nearby. Wrong bug = wrong fix.
-- [ ] The failure is reproducible across multiple runs (or, for non-deterministic bugs, reproducible at a high enough rate to debug against).
-- [ ] You have captured the exact symptom (error message, wrong output, slow timing) so later phases can verify the fix actually addresses it.
-
-### Minimise
-
-Once it's red, shrink the repro to the **smallest scenario that still goes red**. Cut inputs, callers, config, data, and steps **one at a time**, re-running the loop after each cut — keep only what's load-bearing for the failure.
-
-Why bother: a minimal repro shrinks the hypothesis space in Phase 3 (fewer moving parts left to suspect) and becomes the clean regression test in Phase 5.
-
-Done when **every remaining element is load-bearing** — removing any one of them makes the loop go green.
-
-Do not proceed until you have reproduced **and** minimised.
-
-## Phase 3 — Hypothesise
-
-Generate **3–5 ranked hypotheses** before testing any of them. Single-hypothesis generation anchors on the first plausible idea.
-
-Each hypothesis must be **falsifiable**: state the prediction it makes.
-
-> Format: "If <X> is the cause, then <changing Y> will make the bug disappear / <changing Z> will make it worse."
-
-If you cannot state the prediction, the hypothesis is a vibe — discard or sharpen it.
-
-**Show the ranked list to the user before testing.** They often have domain knowledge that re-ranks instantly ("we just deployed a change to #3"), or know hypotheses they've already ruled out. Cheap checkpoint, big time saver. Don't block on it — proceed with your ranking if the user is AFK.
-
-## Phase 4 — Instrument
-
-Each probe must map to a specific prediction from Phase 3. **Change one variable at a time.**
-
-Tool preference:
-
-1. **Debugger / REPL inspection** if the env supports it. One breakpoint beats ten logs.
-2. **Targeted logs** at the boundaries that distinguish hypotheses.
-3. Never "log everything and grep".
-
-**Tag every debug log** with a unique prefix, e.g. `[DEBUG-a4f2]`. Cleanup at the end becomes a single grep. Untagged logs survive; tagged logs die.
-
-**Perf branch.** For performance regressions, logs are usually wrong. Instead: establish a baseline measurement (timing harness, `performance.now()`, profiler, query plan), then bisect. Measure first, fix second.
-
-## Phase 5 — Fix + regression test
-
-Write the regression test **before the fix** — but only if there is a **correct seam** for it.
-
-A correct seam is one where the test exercises the **real bug pattern** as it occurs at the call site. If the only available seam is too shallow (single-caller test when the bug needs multiple callers, unit test that can't replicate the chain that triggered the bug), a regression test there gives false confidence.
-
-**If no correct seam exists, that itself is the finding.** Note it. The codebase architecture is preventing the bug from being locked down. Flag this for the next phase.
-
-If a correct seam exists:
-
-1. Turn the minimised repro into a failing test at that seam.
-2. Watch it fail.
-3. Apply the fix.
-4. Watch it pass.
-5. Re-run the Phase 1 feedback loop against the original (un-minimised) scenario.
-
-## Phase 6 — Cleanup + post-mortem
-
-Required before declaring done:
-
-- [ ] Original repro no longer reproduces (re-run the Phase 1 loop)
-- [ ] Regression test passes (or absence of seam is documented)
-- [ ] All `[DEBUG-...]` instrumentation removed (`grep` the prefix)
-- [ ] Throwaway prototypes deleted (or moved to a clearly-marked debug location)
-- [ ] The hypothesis that turned out correct is stated in the commit / PR message — so the next debugger learns
-
-**Then ask: what would have prevented this bug?** If the answer involves architectural change (no good test seam, tangled callers, hidden coupling) hand off to the `/improve-codebase-architecture` skill with the specifics. Make the recommendation **after** the fix is in, not before — you have more information now than when you started.
+Mention a broader architecture issue only when the evidence supports it; do not launch another audit or refactor unless requested or necessary for the authorized repair.

.agents/skills/diagnosing-bugs/scripts/hitl-loop.template.sh

@@ -11,9 +11,6 @@
 #   capture VAR "<question>"      → show question, read response into VAR
 #
 # At the end, captured values are printed as KEY=VALUE for the agent to parse.
-#
-# `capture` prints its value back to the terminal, where the agent reads it — so
-# capture observations, and leave signing in to the user as a `step`.
 
 set -euo pipefail