Public reference for the on-disk .tasks/STATUS.md block format the autonomous
poller parses: header regex, status emoji, and the **Weight:** / **Notify:** /
**Requirements:** fields. Ships with factory where the internal wiki and MCP
source can't reach. Distinct from delegate-task (MCP-tool delegation) and
using-tasks (board mechanics).
Authored via superpowers:writing-skills TDD:
- RED: 3 baseline subagents w/o skill — 2/3 used ###/bullet headers the parser
cannot recognize as a task, 2/3 omitted **Weight:** (invented risk/tier/
claimable-by), 2/3 put notify in prose, 1/3 used 🟢 for a ready task.
- GREEN: 2 fresh subagents w/ skill — both parser-valid, incl. correct
**Weight:** needs-human for the critical-infra scenario.
- REFACTOR: no new format loopholes.
Ground truth verified vs live source (status-md.ts parser, claim.ts gate,
fleet-router.js routing): missing Weight finds no backend tier -> poller parks
to blocked, so Weight is operatively required for pickup.
Closes [create-task-format-for-poller-skill]. Install to ~/.claude/skills +
hermes mapping deferred as follow-up.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
needs-human keep-or-drop on the markitdown MCP tool + cross-cutting edit to
user-global ~/.claude.json. Verified live state (mcpServers.markitdown present,
container respawned, image 1.52GB) then called consult before mutating; returned
status:halt (consult_policy=human-only). Checkpointed without guessing past the
halt: board block → blocked, added per-task file with resume brief + decision
trail. No config/containers/image touched.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Reviewed the MCP→CLI rewrite of skills/using-markitdown/SKILL.md.
Acceptance (3/3) + 2 bonus checks, all green:
- No mcp__markitdown__ in SKILL.md (grep 0; only 2 negative "Docker"
mentions explaining the old mount caveat no longer applies).
- CLI examples correct: markitdown 0.1.6 on PATH; -o/-x/-m/stdin flags
match `markitdown --help` verbatim.
- Version bumped 1.0.0 -> 1.0.1 (PATCH).
- dist/using-markitdown.skill consistent (v1.0.1, no mcp refs).
Informational finding (non-blocking): at review time `docker ps` shows a
markitdown-mcp:latest container respawned from the out-of-scope
mcpServers.markitdown registration in ~/.claude.json. The impl removed the
existing containers correctly and flagged this respawn in the concept page.
Filed follow-up [using-markitdown-mcp-deregister] (needs-human: keep-or-drop
decision on the MCP registration).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Reviewed using-tasks v1.3.0 STATUS.md-bloat fix + concept page.
- Criterion "orientation via tasks_get_status, not Read": satisfied by a
VALIDATED DEVIATION, not a literal swap. Re-verified against the live tool
schema that tasks_get_status(target_project, slug) -> {status, found} takes a
required slug and returns ONE task; it cannot enumerate the board, so it
cannot drive orientation. Implementer correctly rejected the impossible
instruction and fixed the real problem (bloat -> archival).
- No regression: orientation still reads local STATUS.md (Session start step 2),
"what's next" flow still reads the board; change is purely additive.
- Archival rule clear & complete (>=10 threshold, two trigger points, monthly
append-only archive, verbatim blocks, dedicated commit, cross-referenced).
Informational (non-blocking): this repo's own STATUS.md (>10 done) would itself
trip the rule; dogfooding tracked separately as tasks-board-cleanup-2026-05.
No follow-up tasks. Verdict appended to concept page + wiki log.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Non-implementer review of skills/using-system-snapshot (v0.1.0). All three
acceptance criteria pass:
- trigger phrases cover real scenarios (4/4 positives + clean negatives)
- no-claim-without-snapshot rule explicit (4 places)
- output format brief (three lines, verified vs live payload)
Evidence: live meta_system_snapshot call confirms the documented poller/docker/
tasks contract; 9 fresh-context subagents over a simulated registry (real
descriptions + using-vds-ops/using-projects-meta/using-tasks competitors) routed
8 cleanly, incl. no false-positive on a docker-compose.yml edit.
3 informational findings, none blocking:
1. cross-project task-count phrasings overlap with using-projects-meta (by-design)
2. local-container deep diagnosis unowned — vds-ops scope, not this skill
3. deployment scaffold missing — not installed, not in hermes/mapping.yaml,
no -install/-hermes-mapping/-test-trigger baseline tasks
No SKILL.md edits -> no version bump. TDD N/A (review of markdown policy).
Review outcome recorded in .wiki/concepts/using-system-snapshot-design.md + log.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Review of session_break authoring side in delegate-task SKILL.md v0.2.2.
All 4 acceptance criteria met by inspection:
- Q6 placed directly after Q5 notify (0-indexed item 5.)
- Template field with example values + inline comment
- Usage guidance: three cases listed
- Version bumped to v0.2.2
author<->consumer key (session_break) match grep-verified against
using-tasks v1.2.0. 1 informational note (0-indexed numbering, cosmetic),
no blocking findings, no follow-up tasks.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Reviewed session_break impl in using-tasks SKILL.md (commit 9a518fc, v1.2.0).
All 4 acceptance criteria met:
- Rule placement: Task completion step 6, after close (set green + commit),
before any tasks_claim_next — order correct.
- SESSION BOUNDARY message: verbatim match to design string (slug + hint).
- Absent flag: behaviour unchanged (no regression).
- Version: bumped to v1.2.0 in 9a518fc (now 1.3.0 from later archival task).
No blocking findings, no follow-up tasks.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
MINOR bump 1.2.0 -> 1.3.0. Adds a done-task archival rule: when >=10
green done blocks pile up in STATUS.md (checked at Session start step 7
and Task completion step 7), move them verbatim to
.tasks/archive/YYYY-MM.md (append, monthly file, one-time header,
committed on its own), leaving only active/paused/ready/blocked on the
board. This is the root-cause fix for the recurring "huge STATUS.md"
complaint -- orientation still reads the local board, but the board is
kept small so the read stays cheap.
Deliberately did NOT follow the task's literal instruction to swap
Read STATUS.md for tasks_get_status in the orientation flow: that rests
on a factual error. tasks_get_status returns ONE task's live status by a
known slug and cannot enumerate the board; tasks_aggregate is
cross-project + cache-based and does not index ready/done (its docs say
read STATUS.md directly for the current project). So no projects-meta
tool replaces the orientation board-read. The skill now warns against
both tools for board enumeration and points tasks_get_status at its real
single-task use.
Concept page concepts/using-tasks-status-archival.md + index + log
document the deviation for the paired review task. TDD N/A (markdown
policy). hermes/mapping + install untouched (separate baseline tasks).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
