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.
git clone --depth 1 https://github.com/gonnagetapower/kelvia-mcpWrote 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/gonnagetapower/kelvia-mcp/capture)<a href="https://agentmods.dev/commands/gonnagetapower/kelvia-mcp/capture"><img src="https://agentmods.dev/badge/commands/gonnagetapower/kelvia-mcp/capture/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/gonnagetapower/kelvia-mcp/capture"><img src="https://agentmods.dev/badge/commands/gonnagetapower/kelvia-mcp/capture.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 | $0.00014 | $0.00254 |
| Opus 5 | $0.00007 | $0.00127 |
| Sonnet 5 | $0.00003 | $0.00051 |
| Haiku 4.5 | $0.00001 | $0.00025 |
Grade A, and why
capture 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 9d 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.
What it actually says
Take what this session actually produced and put it on the board, so it survives the session ending.
-
Re-read the conversation and list, for yourself, the work that came out of it: things done, things deliberately left undone, follow-ups discovered along the way, and problems found but not fixed.
-
Drop anything already on the board. Check with
list_tasksbefore filing — duplicates are the fastest way to make a board useless. -
Show the user the proposed tasks as a short list, with the column each would land in, and ask them to confirm or cut. Do not file first and apologise after.
-
On confirmation, create them with
create_task. Titles state the outcome; descriptions carry the reasoning and any reproduction steps from this session. -
For work that was finished during the session, file it in the done column and log the time with
add_task_worklogif the session makes the duration clear. If it does not, leave the time off rather than guessing.
Argument, if the user supplied one, narrows the scope: $ARGUMENTS
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.
- 9d ago First seen · 26 lines · 14 tokens per session scan A 263ddd00c294
capture is a command published in the GitHub repository gonnagetapower/kelvia-mcp (1 stars, last pushed 25d ago), licensed MIT. It adds 14 tokens to every session and 254 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
status
Display project status, active tracks, and next actions.
ijfw-status
Show IJFW state -- mode, routing, memory, recent activity, codebase index, settings. Use when you want the at-a-glance banner you'd otherwise get at session start.
pm-done
Close a todo (TODO-xxx), sync completed.md, refresh overview.
pm-charter
Create, import, discover, approve, or skip project charter. No-arg form is an interactive wizard.
_closing
A set of closing rules for project-management commands that change the .pm/ project-management folder. It controls the language of summaries and links shown in the final response.
prp-prd
Interactive PRD generator - problem-first, hypothesis-driven product spec with back-and-forth questioning.