Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add HirogaKatageri/hirokata --skill dashboardgit clone --depth 1 https://github.com/HirogaKatageri/hirokataWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hirogakatageri/hirokata/dashboard)<a href="https://agentmods.dev/skills/hirogakatageri/hirokata/dashboard"><img src="https://agentmods.dev/badge/skills/hirogakatageri/hirokata/dashboard/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hirogakatageri/hirokata/dashboard"><img src="https://agentmods.dev/badge/skills/hirogakatageri/hirokata/dashboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00114 | $0.03987 |
| Opus 5 | $0.00057 | $0.01994 |
| Sonnet 5 | $0.00023 | $0.00797 |
| Haiku 4.5 | $0.00011 | $0.00399 |
Grade A, and why
dashboard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guild Dashboard — the whole board as one page
Read-only. You build a file; you change no state. There is no generator script — you query
the warehouse and write the page yourself. Load guild:warehouse for the connection ritual.
Two rules make this page safe, and they are not style preferences. The board holds text the guild master and four kinds of agent typed — requirement titles, bug reports, review findings, work logs — and a page that executes a requirement title is a real security defect. Read them before you write a line:
- The data crosses as a JSON island with
<,>and&escaped, because</script>is valid inside a JSON string and still closes the element. - Everything renders through
textContent. NeverinnerHTML.
Step 1 — is there a guild?
[ -f .guild/config.yaml ] || echo "no guild here"
If it is missing, say this and stop:
No guild board found. Run /guild:check-in to initialize and start your first work session.
Step 2 — get the data, as one escaped JSON document
One query, one row, one column — so -m list never inserts a separator, and free text stays
byte-exact. The three replace()s do the escaping inside the engine, before the value ever
touches a shell:
export PATH="$HOME/.turso:$PATH"
cat > /tmp/guild-dash.sql <<'SQL'
SELECT replace(replace(replace(json_object(
'brief', (SELECT json_group_array(json_object('fact',fact,'value',value)) FROM v_brief),
'goals', (SELECT json_group_array(json_object('id',id,'status',status,'priority',priority,
'projects',projects_total,'projects_done',projects_done,
'runnable',projects_runnable,'runnable_ids',runnable_project_ids,
'done',requirements_done,'total',requirements_total,'title',title))
FROM (SELECT * FROM v_goal_progress ORDER BY priority, id)),
'projects', (SELECT json_group_array(json_object('id',id,'goal',goal_id,'ordinal',ordinal,
'status',status,'priority',priority,'concurrent',concurrent,
'isolation',isolation,'worktree',worktree_path,'runnable',runnable,
'reqs',requirements_total,'reqs_done',requirements_done,
'open',tasks_open,'blocked',tasks_blocked,'title',title))
FROM (SELECT * FROM v_project_progress)),
'requirements', (SELECT json_group_array(json_object('id',id,'project',COALESCE(project_id,''),
'status',status,'priority',priority,'total',tasks_total,'done',tasks_done,
'open',tasks_open,'blocked',tasks_blocked,'failed',tasks_failed,'title',title))
FROM (SELECT * FROM v_requirement_progress)),
'tasks', (SELECT json_group_array(json_object('section',section,'n',section_no,'id',id,
'status',status,'who',who,'req',requirement_id,'priority',priority,'title',title))
FROM (SELECT * FROM v_board)),
'blocked', (SELECT json_group_array(json_object('id',id,'reason',reason))
FROM (SELECT * FROM v_blocked_tasks)),
'approvals', (SELECT json_group_array(json_object('id',id,'req',requirement_id,
'status',status,'gate',gate_node_id,'title',title))
FROM (SELECT * FROM v_plans_pending_approval)),
'nodes', (SELECT json_group_array(json_object('id',id,'req',requirement_id,'key',node_key,
'kind',kind,'status',status,'task',COALESCE(task_id,''),
'group',COALESCE(parallel_group,'')))
FROM (SELECT * FROM graph_node ORDER BY requirement_id, id)),
'edges', (SELECT json_group_array(json_object('from',from_node,'to',to_node))
FROM (SELECT * FROM graph_edge ORDER BY from_node, to_node)),
'gates', (SELECT json_group_array(json_object('node',node_id,'kind',kind,'status',status,
'prompt',prompt,'decision',COALESCE(decision,''),'decided',COALESCE(decided_at,'')))
FROM (SELECT * FROM gate ORDER BY node_id)),
'bugs', (SELECT json_group_array(json_object('id',id,'severity',severity,'status',status,
'by',found_by,'req',COALESCE(requirement_id,''),'fix',COALESCE(fix_task_id,''),
'created',created_at,'title',title))
FROM (SELECT * FROM bug ORDER BY id)),
'findings', (SELECT json_group_array(json_object('id',id,'task',task_id,'reviewer',reviewer,
'severity',severity,'disposition',disposition,'file',COALESCE(file,''),
'line',COALESCE(line,0),'fix',COALESCE(fix_task_id,''),'created',created_at,
'summary',summary,'detail',COALESCE(detail,'')))
FROM (SELECT * FROM review_finding ORDER BY id)),
'coverage', (SELECT json_group_array(json_object('id',id,'area',area,'risk',risk,
'spec',COALESCE(spec_path,''),'last',COALESCE(last_inspected_at,''),
'notes',COALESCE(notes,'')))
FROM (SELECT * FROM coverage ORDER BY id)),
'docs', (SELECT json_group_array(json_object('slug',slug,'title',title,'kind',kind,
'status',status,'area',area,'source',source,'created',created_at,
'updated',updated_at,'revisions',revisions,'edges',edges))
FROM (SELECT * FROM v_doc_current)),
'decisions', (SELECT json_group_array(json_object('slug',slug,'title',title,'status',status,
'area',area,'created',created_at,'supersedes',supersedes,
'superseded_by',superseded_by,'governs',governs,'revisions',revisions))
FROM (SELECT * FROM v_decision_log)),
'links', (SELECT json_group_array(json_object('rel',rel,'from_type',from_type,'from',from_id,
'to_type',to_type,'to',to_id,'note',note,'by',created_by))
FROM (SELECT * FROM knowledge_edge ORDER BY id)),
'docs_stale', (SELECT json_group_array(json_object('slug',slug,'title',title,'kind',kind,
'rel',rel,'subject_type',subject_type,'subject',subject_id,
'doc_updated',doc_updated_at,'subject_moved',subject_moved_at))
FROM (SELECT * FROM v_doc_stale)),
'undocumented', (SELECT json_group_array(json_object('id',id,'title',title,
'project',COALESCE(project_id,''),'finished',finished_at,'tasks',tasks_done))
FROM (SELECT * FROM v_undocumented_work)),
'activity', (SELECT json_group_array(json_object('ts',ts,'actor',actor,'verb',verb,
'type',subject_type,'subject',subject_id,'title',subject_title,'phrase',phrase))
FROM (SELECT * FROM v_recent_activity LIMIT 200))
),
'&', char(92) || 'u0026'),
'<', char(92) || 'u003c'),
'>', char(92) || 'u003e');
SQL
tursodb -q -m list .guild/guild.db < /tmp/guild-dash.sql > /tmp/guild-data.json
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 287 lines · 114 tokens per session scan A 08130cf54dab
dashboard is a skill published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 3,987 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
crm-management
Use when an internal 101 goal must manage CRM pipelines, stages, deals, or distribution rules through the current CRM API.
estimate-management
Use when an internal 101 goal must find, read, create, or edit one or many estimates through the existing event API, including sourced or manual positions and their dates.
project-management
Use when an internal 101 goal must create or edit a project, select its customer or price list, manage project expense categories, or copy category settings from another project.
task-management
Use when an internal 101 goal must list, read, open, update, or comment on tasks, including the interactive task detail widget.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…