Borrowing it
Nothing to install: this file belongs to Nitjsefnie-Harness-Commons/daedalus. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Nitjsefnie-Harness-Commons/daedalus/main/.claude/skills/changing-daedalus/SKILL.mdgit clone --depth 1 https://github.com/Nitjsefnie-Harness-Commons/daedalusWrote 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/nitjsefnie-harness-commons/daedalus/changing-daedalus)<a href="https://agentmods.dev/skills/nitjsefnie-harness-commons/daedalus/changing-daedalus"><img src="https://agentmods.dev/badge/skills/nitjsefnie-harness-commons/daedalus/changing-daedalus/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/nitjsefnie-harness-commons/daedalus/changing-daedalus"><img src="https://agentmods.dev/badge/skills/nitjsefnie-harness-commons/daedalus/changing-daedalus.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 | $0.00051 | $0.06804 |
| Opus 5 | $0.00026 | $0.03402 |
| Sonnet 5 | $0.00010 | $0.01361 |
| Haiku 4.5 | $0.00005 | $0.00680 |
Grade A, and why
changing-daedalus 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 2d 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 — 508 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Changing Daedalus
What this repository does differently, and what it has already been burned by. Everything general is left to the skill that owns it: follow the pointers instead of expecting a summary, because a summary here is what stops the skill being read.
| Situation | Where it is governed |
|---|---|
| Implementing any feature or fix | superpowers:test-driven-development |
| Multi-task implementation | Required SDD workflow below |
| Subagent dispatch | agent-routing |
| A bug, a test failure, or behaviour you cannot explain | superpowers:systematic-debugging |
| About to say something works, passes, or is done | superpowers:verification-before-completion |
| Writing a pull request or issue body | .github/PULL_REQUEST_TEMPLATE.md, .github/ISSUE_TEMPLATE/issue.md |
| Architecture, endpoints, exact field names | AGENTS.md |
| Piping a runner, a trailing status echo, an ` | |
| Contribution conventions and the guard-per-layer rule | CONTRIBUTING.md |
| Auditing outgoing co-author trailers | git-coauthorship and CONTRIBUTING.md |
For every feature or fix, regardless of size:
- The lead dispatches the work; it never implements it in its own
context. Implementation goes to an
implementersubagent and review to independent reviewers, because a lead that implements is biased toward its own code and will not catch its own mistakes. The lead verifies claims and orchestrates; it does not write the change.
For an implementation plan with independent tasks in the current session:
- REQUIRED SUB-SKILL: Use
superpowers:subagent-driven-development. - REQUIRED PATCH: Read
subagent-driven-development-patchwhenever that skill is loaded or run; it overrides the reviewer-model guidance and carries the lead-orchestrates rule. - REQUIRED ROUTING: Read
agent-routingbefore every subagent dispatch.
Running the suites
Run them bare - bash-harness-antipatterns owns why, and it covers the
whole family (piping a runner, a trailing status echo, an || true evidence
fallback). What it costs here specifically: a filtered run of a blank-line
truncation check dropped half of a two-line failure message and read as a
serious regression that did not exist, and roughly ten minutes went on a false
alarm manufactured by the filter.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago Changed · +1 lines 1344e994d340
- 5d ago Changed · +31 lines 7c2cfee589d7
- 9d ago First seen · 476 lines · 51 tokens per session scan A ff48b1ef6b4d
changing-daedalus is a skill published in the GitHub repository Nitjsefnie-Harness-Commons/daedalus (1 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 6,804 once invoked, about $0.0003 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 skills, from other repositories
browsertap-bridge-recovery
A troubleshooting guide for restoring the connection between browsertap-mcp and a real Chrome or Edge browser. It covers the browser bridge and its connection checks.
browsertap-default
A browser-automation skill that connects to an already running, logged-in Chrome or Edge browser. It provides fixed procedures for reading pages, interacting with forms, downloading files, and handling browser sessions.
browser
Use this skill when the user says browser, /browser, test in Chrome, inspect a webpage, verify a localhost app, capture screenshots, check console/network errors, run browser QA, or automate browser flows with the Mochi browser MCP.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
qa
QA-test a website or web app and return a 1-5 quality score (5 = flawless, 1 = broken) with evidence. Use when the user wants to test, QA, evaluate, score, or "check how good" a site, page, flow, or app — including a local dev server (e.g. "qa test localhost:5173", "does the checkout work?", "rate this landing page").…
owb
Open Web Bridge (OWB) — drive the user's own real browser with the owb command. Read pages behind their existing logins, gather and cross-check information, fill forms, walk multi-step flows, debug their site, audit responsive/accessibility behavior, and capture or reverse-engineer network traffic. Use this whenever…