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 Samuel0101010/wisp-orchestrator --skill wisp-resumegit clone --depth 1 https://github.com/Samuel0101010/wisp-orchestratorWrote 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/samuel0101010/wisp-orchestrator/wisp-resume)<a href="https://agentmods.dev/skills/samuel0101010/wisp-orchestrator/wisp-resume"><img src="https://agentmods.dev/badge/skills/samuel0101010/wisp-orchestrator/wisp-resume/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/samuel0101010/wisp-orchestrator/wisp-resume"><img src="https://agentmods.dev/badge/skills/samuel0101010/wisp-orchestrator/wisp-resume.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 | $0.00069 | $0.00844 |
| Opus 5 | $0.00034 | $0.00422 |
| Sonnet 5 | $0.00014 | $0.00169 |
| Haiku 4.5 | $0.00007 | $0.00084 |
Grade A, and why
wisp-resume scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- bash: `curl -s http://127.0.0.1:${WISP_PORT:-4400}/api/health` How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WISP — Resume Run
Resume a paused harness run.
Platform note: snippets below show both bash and PowerShell forms. Pick the one matching the user's shell. The bash form also runs from Git Bash / WSL on Windows.
Preflight
Health-check the server.
- bash:
curl -s http://127.0.0.1:${WISP_PORT:-4400}/api/health - PowerShell:
Invoke-RestMethod -Uri "http://127.0.0.1:$($env:WISP_PORT ?? 4400)/api/health"
Bail with a friendly error if not 200 — tell the user to run /wisp-dashboard first.
Steps
-
List resumable runs:
# bash curl -s "http://127.0.0.1:${WISP_PORT:-4400}/api/runs?resumable=true"# PowerShell $port = if ($env:WISP_PORT) { $env:WISP_PORT } else { 4400 } Invoke-RestMethod -Uri "http://127.0.0.1:$port/api/runs?resumable=true"Response:
{"runs": [{"id":"...", "planId":"...", "status":"paused", "pausedReason":"...", "resumeAt": ..., ...}]}. -
If 0 resumable runs: tell the user there's nothing to resume and stop.
-
If 1 resumable run: confirm with the user briefly (one sentence summarising the run), then proceed to step 5.
-
If 2+ resumable runs: list them with id, paused-reason, and (if present) resumeAt. Ask the user which one to resume.
-
Resume the chosen run:
# bash curl -s -X POST "http://127.0.0.1:${WISP_PORT:-4400}/api/runs/<runId>/resume"# PowerShell Invoke-RestMethod -Method Post -Uri "http://127.0.0.1:$port/api/runs/<runId>/resume"The response includes the resumed status. Print the run URL:
http://127.0.0.1:${WISP_PORT:-4400}/projects/<projectId>/run/<runId>
Errors
409Conflict from /resume → the run is no longer paused (raced with another resume / completed in the meantime). Re-list and try again.503from /resume → auth probe failed; tell the user to runclaude login.
Notes
- The
?resumable=truefilter only surfaces runs that need an explicit resume action: shutdown-recovered runs (status='paused', pausedReason='shutdown') and abrupt-crash runs (status='running' with a stale heartbeat that the server rewrote on boot). Rate-limit pauses auto-resume when theirresumeAttimer fires and only show up here AFTER a server restart that rewrites them to 'shutdown'. - A consecutive-failure pause and a manual /pause are NOT in this list during the same server lifetime — they live in
GET /api/runs?status=paused. Use that endpoint when the user wants to resume one of those instead. - A rate-limit-paused run can be resumed BEFORE its
resumeAtwindow if the user wants to test (it'll just hit the rate-limit again, but that's their call).
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.
- 10d ago First seen · 64 lines · 69 tokens per session scan A 5714001e68db
wisp-resume is a skill published in the GitHub repository Samuel0101010/wisp-orchestrator (4 stars, last pushed 6d ago), licensed Apache-2.0. It adds 69 tokens to every session and 844 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
research
Focused research investigations. Converts questions into structured findings with confidence levels and source citations. Single agent by default; with --parallel (or when the question decomposes into 3+ independent angles) it spawns scout agents whose findings are compressed into a unified brief. Does not make…
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
triage
GitHub issue and PR investigator. Pulls open issues/PRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to…