Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ngocsangyem/MeowKitnpx agentmods add commands/ngocsangyem/meowkit/confluence-setupWrote 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/commands/ngocsangyem/meowkit/confluence-setup)<a href="https://agentmods.dev/commands/ngocsangyem/meowkit/confluence-setup"><img src="https://agentmods.dev/badge/commands/ngocsangyem/meowkit/confluence-setup/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/commands/ngocsangyem/meowkit/confluence-setup"><img src="https://agentmods.dev/badge/commands/ngocsangyem/meowkit/confluence-setup.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 | $0.00018 | $0.00624 |
| Opus 5.5 | $0.00007 | $0.00250 |
| Sonnet 5.5 | $0.00004 | $0.00125 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade B, and why
confluence-setup scanned grade B with 1 finding 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 1mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
2. Ensure `.meowkit/.env` exists. If absent: create empty file, then `chmod 0600 .meowkit/.env`. How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mk:confluence-setup
Walk the user through Confluence Cloud credential setup for the mk:confluence-* skills.
Steps
-
Verify
.claude/scripts/bin/setup-workflowran andconfluence-asbinary exists at.claude/skills/.venv/bin/confluence-as. If not, instruct:.claude/scripts/bin/setup-workflow. -
Ensure
.meowkit/.envexists. If absent: create empty file, thenchmod 0600 .meowkit/.env. -
Check whether
MEOW_CONFLUENCE_*vars are already populated:grep -c '^MEOW_CONFLUENCE_' .meowkit/.env || trueIf present (count >= 3): ask user whether to overwrite. If overwriting, comment out the old lines (do not delete; user may want to recover).
-
Prompt user for the three values via
AskUserQuestion:- Site URL — must end in
.atlassian.net. Validate with regex. - Email — Atlassian account email.
- API token — instruction text: "Generate one at https://id.atlassian.com/manage-profile/security/api-tokens then paste here. The token will not be displayed in chat."
- Site URL — must end in
-
Append to
.meowkit/.envvia>>Bash redirection (do NOT echo back — keeps token out of transcript):MEOW_CONFLUENCE_SITE_URL=... MEOW_CONFLUENCE_EMAIL=... MEOW_CONFLUENCE_API_TOKEN=... -
Re-run
chmod 0600 .meowkit/.env. -
Validate by running:
bash .claude/skills/confluence/scripts/confluence-as.sh space list 2>&1 | head -20Expect non-error JSON output. If the wrapper exits 2/3/127: surface the error and offer to retry.
-
Optional channel-detection smoke (recommended once per install):
bash .claude/skills/confluence/scripts/smoke-live.shTells the user whether to set
MEOW_CONFLUENCE_STDOUT_FILTER=trim-tail. -
On success print: "Confluence skills ready. Try: 'analyze spec for page ' to invoke mk:confluence-spec-analyst once it ships, or 'show me page ' for mk:confluence-page."
Notes
- Does NOT write credentials to
.claude/settings.local.json(the wrapper rejects that path). - Token never echoed in transcript — use Bash heredoc /
>>redirection so the token value never appears in chat output. - Cloud-only — refuse Server/DC URLs at step 4.
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.
- 1mo ago First seen · 54 lines · 18 tokens per session scan B 8d61a6e46311
confluence-setup is a command published in the GitHub repository ngocsangyem/MeowKit (15 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 624 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
valuation-methods
Valuation methods analysis — multiples, DCF inputs, PEG integration, valuation assumption extraction.
genshijin-compress
A command for safely shortening Markdown or text files into the genshijin style.
design-form
Design a form with the fewest fields that works, clear labels, and errors that help.
review
Submit a story for verification (In Progress → In Review, no PR yet).
standup
Alias of /board — the async sprint snapshot.
enum-udp
UDP scan + service follow-up — top ports first, full sweep only when justified.