From 0d35139b8d35e6be5e7d7ebfc3711079a8ee09f8 Mon Sep 17 00:00:00 2001 From: Paul Buetow Date: Wed, 8 Jul 2026 17:26:53 +0300 Subject: Update content for gemtext --- gemfeed/2026-07-09-unveiling-hexai.gmi | 5 +++++ gemfeed/2026-07-09-unveiling-hexai.gmi.tpl | 5 +++++ gemfeed/atom.xml | 7 ++++++- index.gmi | 2 +- uptime-stats.gmi | 24 ++++++++++++------------ 5 files changed, 29 insertions(+), 14 deletions(-) diff --git a/gemfeed/2026-07-09-unveiling-hexai.gmi b/gemfeed/2026-07-09-unveiling-hexai.gmi index f3a5e381..90d4afea 100644 --- a/gemfeed/2026-07-09-unveiling-hexai.gmi +++ b/gemfeed/2026-07-09-unveiling-hexai.gmi @@ -326,6 +326,11 @@ Urgency: 7.8 Tags: agent ``` +This is where it becomes useful for agentic coding. There is an agent skill and a slash command built on top of `ask`: the `agent-task-management` skill knows how to read and update the `ask` task list, and the `/work-on-tasks` command uses that skill to work through a whole backlog on its own — pick the next actionable task, hand it to a fresh sub-agent, mark it done, and continue until nothing actionable is left. That is pretty useful after a planning session where you created a bunch of tasks with their proper dependencies set: point the agent at the project, run `/work-on-tasks`, and it chews through the queue one task at a time. + +=> https://codeberg.org/snonux/dotfiles/src/branch/master/prompts/skills/agent-task-management agent-task-management skill +=> https://codeberg.org/snonux/dotfiles/src/branch/master/prompts/commands/work-on-tasks.md /work-on-tasks command + ## Running multiple providers side by side One feature I use more than I expected: per-surface model lists. In `config.toml` you can configure several providers or models for the same entry point, and Hexai fans the request out to all of them in parallel. diff --git a/gemfeed/2026-07-09-unveiling-hexai.gmi.tpl b/gemfeed/2026-07-09-unveiling-hexai.gmi.tpl index d7c34a77..27c7291e 100644 --- a/gemfeed/2026-07-09-unveiling-hexai.gmi.tpl +++ b/gemfeed/2026-07-09-unveiling-hexai.gmi.tpl @@ -312,6 +312,11 @@ Urgency: 7.8 Tags: agent ``` +This is where it becomes useful for agentic coding. There is an agent skill and a slash command built on top of `ask`: the `agent-task-management` skill knows how to read and update the `ask` task list, and the `/work-on-tasks` command uses that skill to work through a whole backlog on its own — pick the next actionable task, hand it to a fresh sub-agent, mark it done, and continue until nothing actionable is left. That is pretty useful after a planning session where you created a bunch of tasks with their proper dependencies set: point the agent at the project, run `/work-on-tasks`, and it chews through the queue one task at a time. + +=> https://codeberg.org/snonux/dotfiles/src/branch/master/prompts/skills/agent-task-management agent-task-management skill +=> https://codeberg.org/snonux/dotfiles/src/branch/master/prompts/commands/work-on-tasks.md /work-on-tasks command + ## Running multiple providers side by side One feature I use more than I expected: per-surface model lists. In `config.toml` you can configure several providers or models for the same entry point, and Hexai fans the request out to all of them in parallel. diff --git a/gemfeed/atom.xml b/gemfeed/atom.xml index 4d8934b2..13b1ef7e 100644 --- a/gemfeed/atom.xml +++ b/gemfeed/atom.xml @@ -1,6 +1,6 @@ - 2026-07-08T17:18:58+03:00 + 2026-07-08T17:26:44+03:00 foo.zone feed To be in the .zone! @@ -373,6 +373,11 @@ Urgency: 7.8 Tags: agent
+This is where it becomes useful for agentic coding. There is an agent skill and a slash command built on top of ask: the agent-task-management skill knows how to read and update the ask task list, and the /work-on-tasks command uses that skill to work through a whole backlog on its own — pick the next actionable task, hand it to a fresh sub-agent, mark it done, and continue until nothing actionable is left. That is pretty useful after a planning session where you created a bunch of tasks with their proper dependencies set: point the agent at the project, run /work-on-tasks, and it chews through the queue one task at a time.
+
+agent-task-management skill
+/work-on-tasks command
+

Running multiple providers side by side



One feature I use more than I expected: per-surface model lists. In config.toml you can configure several providers or models for the same entry point, and Hexai fans the request out to all of them in parallel.
diff --git a/index.gmi b/index.gmi index 0466b2c2..3fc2187a 100644 --- a/index.gmi +++ b/index.gmi @@ -1,6 +1,6 @@ # Hello! -> This site was generated at 2026-07-08T17:19:04+03:00 by `Gemtexter` +> This site was generated at 2026-07-08T17:26:50+03:00 by `Gemtexter` Welcome to the foo.zone! diff --git a/uptime-stats.gmi b/uptime-stats.gmi index ce438037..35fe0164 100644 --- a/uptime-stats.gmi +++ b/uptime-stats.gmi @@ -1,6 +1,6 @@ # My machine uptime stats -> This site was last updated at 2026-07-08T17:19:04+03:00 +> This site was last updated at 2026-07-08T17:26:49+03:00 The following stats were collected via `uptimed` on all of my personal computers over many years and the output was generated by `goprecords`, the global uptime records stats analyser of mine. @@ -13,7 +13,7 @@ Also check out my blog post: => ./gemfeed/2023-05-01-unveiling-guprecords:-uptime-records-with-raku.gmi Unveiling `guprecords.raku`: Uptime records with Raku (and also there is a version in Go now) -> Uptime stats were last updated Wed 8 Jul 17:19:04 EEST 2026 +> Uptime stats were last updated Wed 8 Jul 17:26:50 EEST 2026 ## Top 20 Uptime's by Host @@ -128,10 +128,10 @@ Boots is the total number of host boots over the entire lifespan. | 10. | makemake | 81 | Linux 6.9.9-200.fc40.x86_64 | 2025-11-16 13:55 | | 11. | uranus | 59 | NetBSD 10.1 | 2025-05-06 15:38 | | 12. | pluto | 51 | Linux 3.2.0-4-amd64 | 2023-02-18 10:13 | -| 13. | *fishfinger | 50 | OpenBSD 7.8 | 2026-07-07 23:34 | -| 14. | mega15289 | 50 | Darwin 23.4.0 | 2024-05-28 18:14 | -| 15. | *mega-m3-pro | 50 | Darwin 25.5.0 | 2026-07-08 14:04 | -| 16. | *blowfish | 50 | OpenBSD 7.8 | 2026-07-07 23:31 | +| 13. | mega15289 | 50 | Darwin 23.4.0 | 2024-05-28 18:14 | +| 14. | *fishfinger | 50 | OpenBSD 7.8 | 2026-07-07 23:34 | +| 15. | *blowfish | 50 | OpenBSD 7.8 | 2026-07-07 23:31 | +| 16. | *mega-m3-pro | 50 | Darwin 25.5.0 | 2026-07-08 14:04 | | 17. | t450 | 46 | FreeBSD 14.2-RELEASE | 2026-01-02 08:37 | | 18. | phobos | 40 | Linux 3.4.0-CM-g1dd7cdf | 2023-02-18 10:13 | | 19. | mega8477 | 40 | Darwin 13.4.0 | 2023-02-18 10:12 | @@ -166,7 +166,7 @@ Score is calculated by combining all other metrics. | 17. | tauceti-f | 108 | Linux 3.2.0-3-amd64 | 2021-07-26 16:48 | | 18. | tauceti-e | 96 | Linux 3.2.0-4-amd64 | 2021-07-26 16:48 | | 19. | callisto | 86 | Linux 4.0.4-303.fc22.x86_64 | 2021-07-26 16:48 | -| 20. | *f0 | 85 | FreeBSD 15.1-RELEASE | 2026-07-08 14:00 | +| 20. | *f1 | 85 | FreeBSD 15.1-RELEASE | 2026-07-08 14:00 | +-----+----------------+-------+-----------------------------------+------------------+ ``` @@ -190,14 +190,14 @@ Boots is the total number of host boots over the entire lifespan. | 10. | *OpenBSD 7... | 110 | | 11. | Darwin 13... | 40 | | 12. | FreeBSD 5... | 25 | -| 13. | Linux 2... | 22 | -| 14. | Darwin 23... | 22 | +| 13. | Darwin 23... | 22 | +| 14. | Linux 2... | 22 | | 15. | Darwin 24... | 22 | | 16. | Darwin 21... | 17 | | 17. | Darwin 15... | 15 | | 18. | Darwin 22... | 12 | -| 19. | *Darwin 25... | 11 | -| 20. | Darwin 18... | 11 | +| 19. | Darwin 18... | 11 | +| 20. | *Darwin 25... | 11 | +-----+----------------+-------+ ``` @@ -259,7 +259,7 @@ Score is calculated by combining all other metrics. | 17. | Darwin 18... | 32 | | 18. | Darwin 22... | 30 | | 19. | Darwin 15... | 29 | -| 20. | FreeBSD 13... | 25 | +| 20. | FreeBSD 5... | 25 | +-----+----------------+-------+ ``` -- cgit v1.2.3