grant/standards
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix doc drift surfaced by doc-auditor: mark /roundup built, correct Current state and a cross-ref

Browse Source
This commit is contained in:
Keysat
2026-06-14 11:22:17 -05:00
parent 04651503d2
commit b55ba13277
3 changed files with 17 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ROADMAP.md
+7 -22
View File
@@ -42,29 +42,14 @@ how the standard gets *adopted* into a repo (a `/harden` command that installs t
linter+hook for the detected stack?); whether to define a minimal "agentic-ops baseline"
checklist doc alongside the other four standards docs.
## 2. `roundup` — cross-project status agent (the inverse of capture/triage)
## 2. `roundup` — cross-project status command ✅ BUILT
**Why:** a global "what should I do next / which project to focus on" view. Capture/triage
push items *down* into project repos; roundup reads back *up* across all of them.
**Shape:** a command (`/roundup`, run from `~/Projects`) that fans out one read-only
subagent per repo to read that repo's `AGENTS.md` (`## Current state`) and `ROADMAP.md`,
plus reads the standards `INBOX.md` for not-yet-triaged items. It synthesizes **one
aggregated to-do list across all projects, grouped by priority**, including items that
haven't been pushed down to a repo yet. Mirror `full-eval`'s orchestrator pattern: fan out,
then synthesize into one report; the per-repo readers can be the generic `Explore` agent or
a small dedicated reader.
**Division of labor (the user's explicit call):** the agent *reads and reports* — it
gathers and presents findings grouped by priority; it does **not** decide the best use of
time. Prioritizing across projects is a back-and-forth the user does on top of the report.
So the output is a clean, evidence-backed inventory, and the "what's actually worth doing
now" conversation happens after, in the main thread.
**Open questions:** which folders count as "my projects" (scan `~/Projects`, skip non-repos
and the standards repo itself?); how to keep it cheap (cap readers, summarize hard); whether
roundup output is ephemeral or written to a `STATUS.md` in the standards repo for diffing
over time like `EVALUATION.md`.
Built and live: `guides/roundup.md` + `adapters/claude/commands/roundup.md`. Fans out a
read-only reader per repo over AGENTS.md/ROADMAP.md, folds in the inbox, and synthesizes one
priority-grouped to-do list across all projects; reads and reports only (prioritizing stays
with the user). **Remaining option:** output is shown inline by default — decide later
whether to also persist a `STATUS.md` in the standards repo for diffing over time like
`EVALUATION.md`.
## 3. Deterministic inbox surfacing — SessionStart hook (optional upgrade over the portable line)