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 sfc-gh-eraigosa/dotfiles --skill wispr-flow-debuggit clone --depth 1 https://github.com/sfc-gh-eraigosa/dotfilesWrote 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/sfc-gh-eraigosa/dotfiles/wispr-flow-debug)<a href="https://agentmods.dev/skills/sfc-gh-eraigosa/dotfiles/wispr-flow-debug"><img src="https://agentmods.dev/badge/skills/sfc-gh-eraigosa/dotfiles/wispr-flow-debug/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/sfc-gh-eraigosa/dotfiles/wispr-flow-debug"><img src="https://agentmods.dev/badge/skills/sfc-gh-eraigosa/dotfiles/wispr-flow-debug.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 | $0.00087 | $0.01964 |
| Opus 5 | $0.00044 | $0.00982 |
| Sonnet 5 | $0.00017 | $0.00393 |
| Haiku 4.5 | $0.00009 | $0.00196 |
Grade A, and why
wispr-flow-debug 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 9d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Wispr Flow triggers (WSL → Windows dev loop)
The Wispr Flow dictation layer lives in opt/Desktop/Apps/scripts/macos.ahk (see
WISPR-FLOW.md for the user runbook). AutoHotkey runs on Windows, but the repo
is edited from WSL, so testing is a deploy → reload → read-log loop across the
boundary. This skill encodes that loop and the gotchas that bite every time.
Mental model (read first)
- Copilot key path: physical Copilot key emits
Win+Shift+F23→ PowerToys Keyboard Manager remaps it to F24 →macos.ahk's*F24::_FlowTriggerDown. - Extra keys path: keys saved in
%LOCALAPPDATA%\dotfiles\flow-triggers.iniare bound at startup to the same_FlowTriggerDown/_FlowTriggerUp. The Copilot key and extra keys share one code path — they cannot diverge by design, so "extra key behaves differently" almost always means an upstream/config issue (PowerToys remap, integrity mismatch, or stale deployed script), not the handler.
Resolve paths (OneDrive-redirected Desktop is common)
PS=powershell.exe
WIN_DESKTOP=$("$PS" -NoProfile -Command "[Environment]::GetFolderPath('Desktop')" | tr -d '\r')
DESKTOP=$(wslpath "$WIN_DESKTOP") # e.g. /mnt/c/Users/<you>/OneDrive/Desktop
DEPLOYED="$DESKTOP/Apps/scripts/macos.ahk"
WIN_TEMP=$("$PS" -NoProfile -Command '$env:TEMP' | tr -d '\r')
DBG="$(wslpath "$WIN_TEMP")/flow-dbg.txt" # where FileAppend DEBUG lines land
INI="$(wslpath "$("$PS" -NoProfile -Command '$env:LOCALAPPDATA' | tr -d '\r')")/dotfiles/flow-triggers.ini"
The loop
1. Deploy the edited script
cp -f opt/Desktop/Apps/scripts/macos.ahk "$DEPLOYED"
diff -q <(tr -d '\r' < "$DEPLOYED") opt/Desktop/Apps/scripts/macos.ahk && echo "deployed == repo"
AutoHotkey does not hot-reload a changed .ahk — you must restart it.
2. Reload AutoHotkey (non-elevated is enough for trigger testing)
First check for an ELEVATED instance — the logon task starts one, and a
non-elevated Stop-Process CANNOT kill it (the failure is silent). It also
shrugs off #SingleInstance Force (UIPI blocks the replace message), so starting
a second copy next to it used to yield duplicate keyboard hooks — one instance
draws a HUD while the other wins the keypress, i.e. a stuck overlay that ignores
Esc. (macos.ahk now guards this with a named mutex: the second copy detects the
first across integrity levels and exits with a pointer to setup-autostart.ps1.)
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.
- 9d ago First seen · 125 lines · 87 tokens per session scan A 649232701e19
wispr-flow-debug is a skill published in the GitHub repository sfc-gh-eraigosa/dotfiles (46 stars, last pushed today), licensed Apache-2.0. It adds 87 tokens to every session and 1,964 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
audit-architecture
Run an application-wide, read-only architecture audit that finds materially useful simplifications in a codebase's data structures, state representation, control flow, algorithms, and ownership boundaries. Fans out bounded read-only agents per subsystem, verifies every finding against the repo, and ranks results P0 to…
flare
Manage Flare error tracking and performance monitoring using the flare CLI. Use when the user wants to list, triage, resolve, snooze, or debug errors; manage projects; create projects and retrieve API keys; check error counts; investigate slow routes, queries, jobs, or commands; view aggregated performance data and…
speeding-up-laravel-tests
Use when Laravel/Pest test suites are slow, CI duration is growing, individual tests take seconds, or the user asks to speed up, optimize, or profile tests. Covers factories, fakes, config caching, XDebug/pcov, BCRYPTROUNDS, LazilyRefreshDatabase, and stray HTTP requests.
review-pr
Review and merge GitHub pull requests for Spatie packages. Use when asked to review a PR, review a pull request, merge a PR, or when given a GitHub PR URL to review. Also triggers on 'review this PR,' 'check this pull request,' 'merge this,' or '/review-pr'. Uses gh CLI for all GitHub operations.
git-commit
This skill should be used BEFORE running any git commit command. Triggers when about to run git commit. Ensures commit messages follow Conventional Commits specification and prompts for the Jira ticket number.
gh-cli
../../../.claude/skills/gh-cli/SKILL.md.