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-new-rungit 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-new-run)<a href="https://agentmods.dev/skills/samuel0101010/wisp-orchestrator/wisp-new-run"><img src="https://agentmods.dev/badge/skills/samuel0101010/wisp-orchestrator/wisp-new-run/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-new-run"><img src="https://agentmods.dev/badge/skills/samuel0101010/wisp-orchestrator/wisp-new-run.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 | $0.00066 | $0.01556 |
| Opus 5 | $0.00033 | $0.00778 |
| Sonnet 5 | $0.00013 | $0.00311 |
| Haiku 4.5 | $0.00007 | $0.00156 |
Grade B, and why
wisp-new-run scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s -X POST http://127.0.0.1:${WISP_PORT:-4400}/api/projects/<projectId>/plan -H 'content-type: application/json' -d '{}' 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:${WISP_PORT:-4400}/api/health` How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WISP — New Run
Take the user from a freeform goal to a running harness execution.
Platform note: snippets below show both bash and PowerShell forms. Pick the one matching the user's shell. The bash form also runs from Git Bash / WSL on Windows.
Inputs needed (ask the user if missing, do not guess)
- Goal: what should the agents accomplish? (1-2 sentences)
- Repo path: absolute path to the git repo to operate in (must exist + be a git repo)
- Template: one of
ts-library | python-backend | refactor-squad | data-pipeline | none - Project name: short identifier (kebab-case if possible)
Preflight
-
Confirm the harness server is up.
- bash:
curl -s http://127.0.0.1:${WISP_PORT:-4400}/api/health - PowerShell:
Invoke-RestMethod -Uri "http://127.0.0.1:$($env:WISP_PORT ?? 4400)/api/health"
If it returns non-200 or refuses connection, tell the user to run
/wisp-dashboardfirst to start the server, then re-run this skill. - bash:
-
Confirm the repo path exists and is a git repo:
git -C <repoPath> rev-parse --git-dir. If not, ask the user to fix the path or rungit initin it.
Steps
-
Create project:
# bash / Git Bash curl -s -X POST http://127.0.0.1:${WISP_PORT:-4400}/api/projects \ -H 'content-type: application/json' \ -d '{"name":"<name>","goal":"<goal>","repoPath":"<repoPath>"}'# PowerShell $port = if ($env:WISP_PORT) { $env:WISP_PORT } else { 4400 } $body = @{ name = "<name>"; goal = "<goal>"; repoPath = "<repoPath>" } | ConvertTo-Json Invoke-RestMethod -Method Post -Uri "http://127.0.0.1:$port/api/projects" ` -ContentType "application/json" -Body $bodyCapture
idfrom the response — this is the projectId. -
Seed team from template (only if template != none):
# bash + jq TEAM=$(curl -s http://127.0.0.1:${WISP_PORT:-4400}/api/team-templates \ | jq -c --arg id <template-id> '.templates[] | select(.id==$id) | .team') curl -s -X PUT http://127.0.0.1:${WISP_PORT:-4400}/api/projects/<projectId>/team \ -H 'content-type: application/json' \ -d "$TEAM"# PowerShell (no jq needed — ConvertFrom-Json gives objects) $port = if ($env:WISP_PORT) { $env:WISP_PORT } else { 4400 } $tpl = Invoke-RestMethod -Uri "http://127.0.0.1:$port/api/team-templates" $team = ($tpl.templates | Where-Object { $_.id -eq "<template-id>" }).team Invoke-RestMethod -Method Put -Uri "http://127.0.0.1:$port/api/projects/<projectId>/team" ` -ContentType "application/json" -Body ($team | ConvertTo-Json -Depth 20)If neither
jqnor PowerShell is available, fetch the templates response into a Python or Node one-liner that prints just.teamfor the chosen id, then pipe that into the PUT body. Do NOT use--data-binary @<file>unless you've actually written the file first. If template == none: tell the user to open the dashboard and configure the team manually, then exit this skill (you cannot create a default team via API today — the dashboard handles defaults).
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 · 119 lines · 66 tokens per session scan B bcc8e8abcec7
wisp-new-run is a skill published in the GitHub repository Samuel0101010/wisp-orchestrator (4 stars, last pushed 6d ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,556 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, 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…