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 MadAppGang/magus --skill framework-signalsgit clone --depth 1 https://github.com/MadAppGang/magusWrote 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/madappgang/magus/framework-signals)<a href="https://agentmods.dev/skills/madappgang/magus/framework-signals"><img src="https://agentmods.dev/badge/skills/madappgang/magus/framework-signals/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/madappgang/magus/framework-signals"><img src="https://agentmods.dev/badge/skills/madappgang/magus/framework-signals.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.01721 |
| Opus 5.5 | $0.00021 | $0.00688 |
| Sonnet 5.5 | $0.00010 | $0.00344 |
| Haiku 4.5 | $0.00005 | $0.00172 |
Grade A, and why
framework-signals 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 1mo 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Framework Signal Reference
Copy-paste-ready signal strings for start-and-watch and watch-pane pattern parameters. Consult this table whenever you need to know what text to look for — whether detecting completion, failure, or that a watcher is still initializing. For the state machine that drives the TDD loop, see terminal:tdd-workflow. For watcher setup, see terminal:terminal-interaction.
Note on Vitest version sensitivity: The
press a to rerunidle signal applies to Vitest < 2.0. Vitest >= 2.0 may use different watch mode output — verify against the running version if results seem off.
Test Watchers
| Framework | Pass Signal | Fail Signal | Still Running | Idle / Waiting |
|---|---|---|---|---|
| Jest | Tests: \d+ passed or All tests passed |
FAIL (with space, line start) or Tests: \d+ failed |
RUNS or Running \d+ tests |
Waiting for file changes |
| Vitest | Tests: \d+ passed or ✓ N tests |
FAIL (line start) or ● Test |
RUNS |
press a to rerun or Waiting... |
| Cargo watch | test result: ok. |
test result: FAILED. or error[E |
[Running 'cargo test'] |
[Watching |
| pytest-watch | N passed in Xs or passed in |
FAILED (caps+space) or N failed |
Ding! Tests running... |
Waiting for changes... |
| Go test (with entr) | ok (line start, space after) |
FAIL (line start) or --- FAIL: |
--- RUN |
(no idle state — entr reruns on change) |
| Bun test | 0 fail in the summary |
✗ lines, or N fail with N > 0 |
bun test v… header |
none: each run ends with Ran N tests across M files. |
| RSpec | N examples, 0 failures |
N examples, N failures |
progress dots | (no watcher state) |
Build Tools
| Tool | Success | Error | In Progress |
|---|---|---|---|
| Cargo build | Finished dev [unoptimized or Finished release |
error[E or error: aborting |
Compiling (line start) |
| Gradle | BUILD SUCCESSFUL in Xs |
BUILD FAILED or > Task :{name} FAILED |
> Task : or > Configure project : |
| Webpack | webpack compiled successfully or compiled successfully |
Failed to compile. or ERROR in |
compiling... or [webpack] |
| Vite HMR | [vite] hmr update /path |
[vite] Internal server error: |
[vite] page reload or [vite] connecting... |
| Vite build | built in Xs or dist/ output lines |
error during build |
transforming... |
| Make | silence + prompt return (exit 0) | make: *** [target] Error N or recipe for target failed |
compiler invocations (cc, g++, clang) |
| Go build | silence + prompt return | ./file.go:\d+:\d+: error or build failed |
no output until done |
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.
- 1mo ago Changed ce462249f637
- 1mo ago Changed 36156e999c28
- 1mo ago First seen · 117 lines · 52 tokens per session scan A 10b9a7774720
framework-signals is a skill published in the GitHub repository MadAppGang/magus (13 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 1,721 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
quality-scan
Run a scoped, read-only quality scan and report exact-candidate evidence, failures and frozen debt. Use for an ad-hoc gate sweep or release preparation; a static scan is not full release acceptance.
e2e-testing
Use when reviewing CI coverage, automated checks, or test strategy related to Implement end-to-end testing. Focus on whether the rule is continuously verified, not just documented.
mirrord-prev-env
Help users create and manage mirrord preview environments — running a modified service as an isolated pod in a shared Kubernetes cluster, scoped by an environment key and HTTP/queue traffic filtering, so teams can validate and review changes against real traffic without affecting live services. Use when a developer…
test-setup
Scaffold the test framework and CI — tests/ directory, engine test runner, GitHub Actions workflow. Once, before the first sprint.
ci
Configure Ginkgo for continuous integration — the recommended CLI flag set and the rationale for each flag (-r -p --randomize-all --randomize-suites --fail-on-pending --fail-on-empty --keep-going --cover --race --trace --json-report --timeout --poll-progress-after/-interval), invoking via go run to pin the CLI to…