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 Szotasz/marveen --skill kanban-auditgit clone --depth 1 https://github.com/Szotasz/marveenWrote 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/szotasz/marveen/kanban-audit)<a href="https://agentmods.dev/skills/szotasz/marveen/kanban-audit"><img src="https://agentmods.dev/badge/skills/szotasz/marveen/kanban-audit/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/szotasz/marveen/kanban-audit"><img src="https://agentmods.dev/badge/skills/szotasz/marveen/kanban-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 37 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Supply Chain · line 43 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- high Supply Chain · line 248 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- high Supply Chain · line 50 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- medium Excessive Agency · line 318 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00062 | $0.14927 |
| Opus 5 | $0.00031 | $0.07463 |
| Sonnet 5 | $0.00012 | $0.02985 |
| Haiku 4.5 | $0.00006 | $0.01493 |
Grade B, and why
kanban-audit scanned grade B with 2 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 2d 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.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s -H "Authorization: Bearer $TOKEN" "http://localhost:$PORT/api/kanban" | python3 -c " Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -H "Authorization: Bearer $TOKEN" "http://localhost:$PORT/api/kanban" | python3 -c " How it starts
The opening of the file, as written. The whole thing — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kanban 4 órás audit
Mikor fut
- 8:00, 12:00, 16:00, 20:00 (kanban-audit cron 0 8,12,16,20)
Autonómia-szint (config-vezérelt, KÖTELEZŐ ELŐSZÖR)
Olvasd be (python3-mal, mert jq NINCS telepítve egy átlagos Linux gépen):
python3 -c "
import json
d=json.load(open('{{INSTALL_DIR}}/store/autonomy-config.json'))
for c in d.get('categories',[]):
if c.get('key') in ('kanban_archive_done','kanban_stuck_nudge'):
print(c['key'], c.get('level'))
" 2>/dev/null
A két kategória szintje szabályozza a 2. és 4. lépést:
kanban_archive_done(2. lépés): level 3 → archiváld magától (alapért). level 2 → NE archiválj, Telegramon javasold ("X db 7+ napos done archiválásra vár, mehet?") és várj jóváhagyást. level 1 → csak jelezd a számot.kanban_stuck_nudge(4. lépés): level 3 → pingeld az assignee-t magától, és CSAK 2 eredménytelen audit-kör után eszkalálj a tulajdonoshoz ({{OWNER_NAME}}) (a komment-történetből látod hányszor pingelted). level 2 → ne pingelj magadtól, Telegramon javasold a tulajdonosnak ({{OWNER_NAME}}). level 1 → csak listázd a beakadt taskokat.
Ha a config hiányzik vagy a kulcs nincs benne → default level 3 (régi viselkedés).
Eljárás
-
State-fájl beolvasás:
store/kanban-audit-state.jsontartalmazzalast_audit_atUnix timestampet. Első futáskor null -> ne pingelj senkit, csak állítsd be a state-et.A tábla eléréséhez a dashboard API-t használd, NE a
sqlite3CLI-t (lásd a Buktatókat). A port a.env-ből jön, hogy nem-alapértelmezett porton is működjön:PORT="$(sed -n 's/^WEB_PORT=//p' {{INSTALL_DIR}}/.env 2>/dev/null | head -1 | tr -d '"')"; PORT="${PORT:-3420}" TOKEN="$(cat {{INSTALL_DIR}}/store/.dashboard-token)" -
Tisztítás: 7+ napos done kártyák archiválása (előbb listázd, aztán archiváld egyesével):
curl -s -H "Authorization: Bearer $TOKEN" "http://localhost:$PORT/api/kanban" | python3 -c "
import json,sys,time cut=int(time.time())-7*86400 for c in json.load(sys.stdin): if c.get('status')=='done' and not c.get('archived_at') and (c.get('updated_at') or 0) < cut: print(c['id']) " | while read -r id; do curl -s -X POST -H "Authorization: Bearer $TOKEN" "http://localhost:$PORT/api/kanban/$id/archive" >/dev/null done
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago Changed · +39 lines ca0d22c604da
- 12d ago First seen · 370 lines · 62 tokens per session scan B 7a1fd7ddb0c4
kanban-audit is a skill published in the GitHub repository Szotasz/marveen (98 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 14,927 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
oma-coordination
Guide for coordinating PM, Frontend, Backend, Mobile, and QA agents on complex projects via CLI. Use for manual step-by-step coordination and workflow guidance.
oma-pm
Product manager that decomposes requirements into actionable tasks with priorities and dependencies. Use for planning, requirements, specification, scope, prioritization, task breakdown, and ISO 21500, ISO 31000, or ISO 38500-aligned planning recommendations.
wayfinder
Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
triage
Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.
to-tickets
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in one file per ticket locally, or native blocking links on a real tracker.