/feedback-review

name: feedback-review
description: "Aggregate feedback signals across all active loops. Reports health, trajectory, overdue checks, regression warnings, and Goodhart's Law violations."
metadata:
  instruction_budget: "55"
  framework_dependency: "mycelium"
  framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin install mycelium@haabe-mycelium."

Feedback Review

Single-place health check across all Mycelium feedback loops. Run periodically or when something feels off.

Preflight: Read target canvas file(s) before any Write/Edit

**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.

**Edit vs Write — different cost profiles** (verified 2026-05-14):

• **`Edit`** (exact-string replacement): `Read` with `limit: 1` satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent `Edit` calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., `purpose.yml` at 800+ lines).
• **`Write`** (full replacement): do a **full Read** first. Write obliterates the file; you should see what you're about to replace. The `limit:1` shortcut is *not* appropriate here.

**ID-bearing entries — scan the ID space before assigning** (added 2026-05-15, v0.23.19): When adding a new component, opportunity, solution, or any other ID-bearing entry to a canvas file, run a Bash grep first to confirm the next ID in your prefix sequence is actually free:

grep -o "<prefix>-[0-9][0-9]*" .claude/canvas/<file>.yml | sort -u -t- -k2 -n | tail -3

Replace `<prefix>` with the canvas's ID prefix (`comp` for landscape, `opp` for opportunities, `sol` for solutions, `ht` for human-tasks, etc.). Then pick the next free integer, **matching the zero-padding already used in that file**. The sort is NUMERIC (`-t- -k2 -n`) rather than lexical, and that is not pedantry: a plain `sort -u` orders `ht-1` after `ht-080`, so on a canvas with inconsistent padding it reports the wrong maximum and the next ID collides. Verified on the dogfood repo 2026-08-13, where lexical sort returned `ht-1` as the highest human-task ID against an actual `ht-080`. `grep -o` is also deliberate: it matches IDs wherever they appear, including cross-references and prose, so an ID that was promised somewhere but not yet defined is not handed out twice. `validate_canvas.py` has a per-file duplicate-ID check (it reports `duplicate id '<id>'`) that catches the failure on CI, but a duplicate can persist in the working tree for days if CI isn't run between edit and discovery; that happened on 2026-05-15, when a duplicate ID was created in `landscape.yml`.

Original failure mode: anti-pattern #7 instance #5, 2026-05-09 — agent conflated Bash `head` with the Read tool, lost ~14k tokens to a Write-fail → remedial-full-Read → re-Write loop. The `limit:1` discipline (graduated 2026-05-14, v0.23.18) prevents the second-order cost where the agent *correctly* follows the rule but full-Reads every time. The ID-scan discipline (graduated 2026-05-15, v0.23.19) prevents the related class where the agent reads enough of the file to satisfy the Edit check but not enough to see existing ID assignments — kin to anti-pattern #8 (Stale State Read).

If this skill writes to multiple canvas files, register each one first (limit:1 for Edit-only paths; full Read for Write paths) AND ID-scan any prefix you intend to assign.

See `${CLAUDE_PLUGIN_ROOT}/engine/agent-operating-contract.md` *Canvas writes — Read before Write* for the canonical rule.

When to Use

• Weekly as part of regular practice
• When metrics aren't moving despite active work
• When the team feels busy but unproductive
• After a failed launch or unexpected regression
• When `/mycelium:diamond-assess` shows stale diamonds

Workflow

1. Check Loop 1 (Immediate) Health

• How many reflexion iterations are averaging? (1 = healthy, 3 = struggling)
• Any corrections logged this session? Are they new patterns or repeats?
• Is the preflight gate catching issues, or are issues slipping through?

2. Check Loop 2 (Incremental) Health

• Are diamond phases progressing? Or stalled?
• Are ICE confidence scores increasing with each GIST step?
• Is the delivery journal being updated? (Empty = no incremental learning)
• Are retrospectives happening after delivery increments?

2b. Parked-Diamond Resume Check

Read `.claude/diamonds/active.yml` for diamonds with `state: parked` (or a `parked_diamonds` section). For each, evaluate its `resume_conditions` against current canvas/world state:

• **Condition met** (the awaited event happened — dependency shipped, evidence arrived, date passed): surface as resumable — "Parked: [id] ([parked_at], condition: '[resume_conditions]'). That condition now holds — ready to resume? Run `/mycelium:diamond-progress` to re-activate."
• **Condition not yet met**: list with its condition (one line) so parked work stays visible, not forgotten.
• **No `resume_conditions` recorded**: flag it — a parked diamond without resume conditions is unreachable by anything but memory; prompt the user to add them or decide park → kill.

This implements the surface promised in `/mycelium:diamond-progress` § Park ("feedback-review and diamond-assess surface parked diamonds with their resume conditions") — a promise that stood unimplemented until the 2026-06-12 gap analysis found no skill read `resume_conditions`. Abandonment is a non-event; nothing else surfaces this.

3. Check Loop 3 (Strategic) Health

**First, the schedule (v0.329.0).** The cadence of every scheduled review is data in `engine/review-schedule.yml`, and one script reads each revie