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 jumppad-labs/spektacular --skill spek-manage-reposgit clone --depth 1 https://github.com/jumppad-labs/spektacularWrote 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/jumppad-labs/spektacular/spek-manage-repos)<a href="https://agentmods.dev/skills/jumppad-labs/spektacular/spek-manage-repos"><img src="https://agentmods.dev/badge/skills/jumppad-labs/spektacular/spek-manage-repos/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/jumppad-labs/spektacular/spek-manage-repos"><img src="https://agentmods.dev/badge/skills/jumppad-labs/spektacular/spek-manage-repos.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 | $0.00033 | $0.02409 |
| Opus 5.5 | $0.00013 | $0.00964 |
| Sonnet 5.5 | $0.00007 | $0.00482 |
| Haiku 4.5 | $0.00003 | $0.00241 |
Grade A, and why
spek-manage-repos 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 24d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Version check first. Before running any other command, run
go run . version check.
- On
status: "match", continue with the skill and produce no version-related output.- On
"mismatch","missing"or"upgrade_needed", the project's settings or installed Spektacular files are out of date: relay the response'sactionmessage to the user, ask them to rungo run . migrate(they can preview it withgo run . migrate --dry-run), and wait for their decision before continuing.- On
"unsupported_format", relay theactionmessage: the project was written by a newer Spektacular, which the user must install before continuing.- Never run
migrateorinit, and never modify installed files yourself. Upgrading is always an explicit, user-initiated action.
STOP. Read this before running any command below. A single successful CLI call, including the very first
repo new, is NOT task completion. It is not a milestone to report back to the user. It is one step out of many in a workflow that you must keep driving, turn after turn, without stopping, until the CLI itself tells you the workflow is finished. If you find yourself about to say "successfully completed" or summarize results after callingrepo neworrepo gotoeven once, you are wrong. Go back and read theinstructionfield you just received, do what it says, and callgotoagain.
What this skill does
This skill covers the go run . repo surface: adding a repo to the current project, inspecting what is already registered, and repairing a repo whose footprint is missing or broken.
Adding a repo is a multi-step interactive workflow owned by the CLI, not a playbook you improvise from. The CLI is the state machine and you are the executor. On each turn it returns JSON containing an instruction field describing exactly one step. You must:
- Read the
instructioncarefully. - Perform the step. Usually that means asking the user exactly one thing, or recording something without asking.
- When the step is complete, run the
gotocommand named at the bottom of the instruction, carrying the answer you just agreed. - Read the next
instructionfrom the new JSON response and repeat.
This is a loop. Do not stop after the first step. Keep looping, step then goto then next instruction then step, until a returned instruction tells you the workflow is finished. Only then report completion to the user.
Concretely: do not stop after repo new. That command only starts the workflow and returns the first instruction, not a registered repo. Seeing a clean JSON response with no error is not a signal to stop; it is the signal to keep going.
The instructions themselves tell you what to ask and what never to say. Follow them as written rather than substituting your own account of how an add works: the wording is the feature.
Inspecting the registry and repairing a footprint are not workflows. They are single commands, covered further down.
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.
- 24d ago Changed · +1 lines d111846a561d
- 1mo ago Changed aedf2ec5fe0c
- 1mo ago First seen · 136 lines · 33 tokens per session scan A 46f160afde93
spek-manage-repos is a skill published in the GitHub repository jumppad-labs/spektacular (20 stars, last pushed 25d ago), licensed Apache-2.0. It adds 33 tokens to every session and 2,409 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-10.
Other skills, from other repositories
gsd-quick
Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents.
gsd-complete-milestone
Archive completed milestone and prepare for next version.
gsd-quick-batch
Batch several /gsd-quick-shaped tasks together — planned, dispatched, and merged as one run.
gsd-workspace
Manage GSD workspaces — create, list, or remove isolated workspace environments.
gsd-inbox
Triage and review open GitHub issues and PRs against project templates and contribution guidelines.
gsd-pause-work
Create context handoff when pausing work mid-phase.