| Age | Commit message (Collapse) | Author |
|---|
|
Document how agents should handle a local toolchain that cannot build
or test the project (e.g. missing libbpf bpf/bpf.h headers, missing
flutter/dart). Preflight the build/test path before trusting it, run
the smallest verifying subset that works, annotate the blocker via
ask annotate, and never claim full verification that did not run.
Scoped to MISSING/incomplete toolchains; slow/long-running test suites
are covered separately by task 9q0.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
|
|
vendored/upstream deps
A sub-agent patched a vendored dependency (libbpfgo) and the change had to
be reverted. When completing a task appears to require changing a vendored,
generated, or upstream dependency, that is a scope boundary: flag it as a
blocker (annotate + report) instead of patching the dep. Added to
2-start-task.md with a pointer from SKILL.md; cross-references the
complete-task commit hygiene and stalled-worker recovery rather than
restating them.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
|
|
Extend the complete-task reference with a 'Commit only in-scope files'
section: at task start and before committing, run git status and split
dirty paths into in-scope vs out-of-scope (pre-existing/unrelated user
edits such as .gitignore/start.sh). Stage only in-scope files by explicit
path, never git add -A/. over a pre-existing dirty worktree, never commit
unrelated files, and record the in-scope/out-of-scope decision in an
ask annotate note. Cross-reference 6-recover-stalled-task.md (broken
partial WIP) to keep the two cases distinct and avoid duplication.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
|
|
Multiple ior/player tasks had a worker stall or get interrupted mid-edit,
leaving broken, uncommitted partial file edits with no documented recovery
path. Add references/6-recover-stalled-task.md covering detect -> assess ->
revert -> resume: how to spot a partial/interrupted edit (dirty worktree,
broken build, half-applied diffs), assess dirty changes against the task
annotations (keep in-scope WIP vs. discard broken edits vs. preserve unrelated
user changes), revert cleanly with scoped git checkout/stash WITHOUT destroying
unrelated work, then re-read annotations, resume from the last known-good
point, and annotate the recovery.
Wire the new reference into SKILL.md's 'When to load what' table and cross-ref
it from 2-start-task.md when picking up an already-started task. Commit
discipline is cross-referenced to 3-complete-task.md rather than duplicated.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
|
|
invocation contract
Agents repeatedly mistook `ask` for a natural-language interface and ran
things like `ask agent-task-management ...` or `ask <free text>`, forcing
orchestrators to paste the correction into every task description.
- Add a prominent STOP blockquote at the very top of SKILL.md stating that
`ask` is a CLI with fixed subcommands and that agent-task-management is a
skill name, never an `ask` subcommand.
- Add an explicit 'Invocation contract' section listing the only valid form
(`ask <subcommand> [args]`) and the real subcommands, derived from existing
content; consolidate the valid/invalid examples there (DRY) with inline
reasons on the invalid ones.
- Mirror the same STOP warning at the top of references/00-context.md and
tighten its rule to point at the contract.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
|
|
Analyse 240 unique completed agent tasks (963 annotations) from
~/Documents/Taskwarrior/AgentsHistory. Identify 7 recurring friction
signals (ask-as-subcommand confusion, stalled-worker recovery, missing
local toolchain, test-suite timeouts, dirty-worktree handling, out-of-scope
dep edits, re-derived r-node deploy) and map each to a specific skill with
concrete fixes. Follow-up agent tasks: 6q0, 7q0, 8q0, 9q0, aq0, bq0, cq0.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
|
|
Factor the per-tag export loop out of taskwarrior::export into a reusable
_taskwarrior::export_tag helper, then use it to export everything tagged
+rocky into a separate tw-rocky-export-*.json set. Those files are picked up
by the existing hostname-keyed import path, so the rocky VM imports them
automatically while work/personal export/import behaviour is unchanged.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
|
|
Documents the fishfinger/blowfish ProxyJump path to reach f-hosts
(paul + doas), r-VMs/rocky (root), and Pis from outside the LAN.
Notes the f3 WireGuard routing caveat and tcsh shell pitfall.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
|
Amp-Thread-ID: https://ampcode.com/threads/T-019ed908-ca57-7251-8ff1-ce10c8c3a787
Co-authored-by: Amp <amp@ampcode.com>
|
|
Amp-Thread-ID: https://ampcode.com/threads/T-019ed908-ca57-7251-8ff1-ce10c8c3a787
Co-authored-by: Amp <amp@ampcode.com>
|
|
Host-specific upload details now live in ~/git/worktime/.uprecords-sync.sh
(kept out of the public dotfiles repo). worktime::supersync calls it via
sh; f3s skill updated accordingly.
Amp-Thread-ID: https://ampcode.com/threads/T-019ed908-ca57-7251-8ff1-ce10c8c3a787
Co-authored-by: Amp <amp@ampcode.com>
|
|
- Implement worktime::uprecords::darwin::import: on earth, push the
Mac's uprecords files synced into the worktime repo to goprecords,
re-labelling host MBDVXJ4XKH9C -> mega-m3-pro.
- f3s skill: add k3s off-LAN remote-access reference (jump via OpenBSD
frontend -> root@r0.wg0 -> kubectl) and document the mega-m3-pro
upload config + earth GOPRECORDS_HOST gotcha in goprecords-uptimed.
Amp-Thread-ID: https://ampcode.com/threads/T-019ed908-ca57-7251-8ff1-ce10c8c3a787
Co-authored-by: Amp <amp@ampcode.com>
|
|
Amp-Thread-ID: https://ampcode.com/threads/T-019ed908-ca57-7251-8ff1-ce10c8c3a787
Co-authored-by: Amp <amp@ampcode.com>
|
|
Check picked random note descriptions against pending +random tasks
and retry up to 3 times before skipping the slot.
Amp-Thread-ID: https://ampcode.com/threads/T-019ed8f8-b1e8-7191-8e47-57244a6d0e44
Co-authored-by: Amp <amp@ampcode.com>
|
|
Probe the LAN /api/server/ping endpoint with a short timeout and use it
when reachable, otherwise fall back to the public HTTPS URL. Fixes the
indefinite hang when running off the home LAN.
Amp-Thread-ID: https://ampcode.com/threads/T-019ed713-5af1-72a2-8a4e-27ee32c1d6d5
Co-authored-by: Amp <amp@ampcode.com>
|
|
|
|
Update the irregular.ninja refresh skill: the album moved to
~/git/irregular.ninja/irregular.ninja and is driven by shuriken (not the old
photoalbum/Makefile). Document the volatile cache/ directory (persistent EXIF
cache parallel to dist/, never deployed) and add a rule that only dist/ is
rsynced to the servers.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
for truecolor
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pane-border-status, window-status format)
|
|
|
|
|
|
|
|
ROCKY label)
|
|
|
|
|
|
|
|
extended-keys-format for tmux 3.2 compat
|
|
|
|
|
|
|
|
|
|
|
|
document LVM layout
|
|
f3 is now running node_exporter and is included in Prometheus
scraping alongside f0/f1/f2. Updated the skill reference to
reflect the new scrape config (192.168.2.133:9100) and include
f3 in the host list.
|
|
|
|
|
