Borrowing it
Nothing to install: this file belongs to PascaleBeier/hitkeep. 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/PascaleBeier/hitkeep/main/.agents/skills/hitkeep-qa/SKILL.mdgit clone --depth 1 https://github.com/PascaleBeier/hitkeepWrote 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/pascalebeier/hitkeep/hitkeep-qa)<a href="https://agentmods.dev/skills/pascalebeier/hitkeep/hitkeep-qa"><img src="https://agentmods.dev/badge/skills/pascalebeier/hitkeep/hitkeep-qa/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/pascalebeier/hitkeep/hitkeep-qa"><img src="https://agentmods.dev/badge/skills/pascalebeier/hitkeep/hitkeep-qa.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 | $0.00057 | $0.00713 |
| Opus 5.5 | $0.00023 | $0.00285 |
| Sonnet 5.5 | $0.00011 | $0.00143 |
| Haiku 4.5 | $0.00006 | $0.00071 |
Grade A, and why
hitkeep-qa 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HitKeep QA
Treat AGENTS.md as repository policy and the live hk QA catalog as workflow truth. Never reproduce the gate matrix, commands, tags, or tool versions in this skill or in a contribution plan.
Select
Use hk_qa_plan whenever it is callable. If it is absent or fails, report whether registration, startup, workspace routing, or task reload is blocking MCP and obtain explicit user approval before using an equivalent CLI action. After approval, discover the planning command through ./hk qa --help and request --output json.
- Use
changedwhile iterating. - Use
completebefore declaring contributor work complete; it runs the deepest locally appropriate gates for affected areas. - Use
pronly for exact unchanged CI parity. - Use
fullwhen release risk, cloud-tagged behavior, container behavior, or the request explicitly requires exhaustive validation.
Before starting an expensive completion profile after source edits, run the smallest cheap hygiene selection from the same source-bound plan unless that unchanged source snapshot already has passing hygiene evidence. This preflight is not completion evidence; it prevents expensive shards from running against source already known to fail basic checks.
Honor planner escalation. Query hitkeep-dev://catalog/qa or the structured CLI catalog for current profiles and gate definitions rather than guessing or copying commands.
Use hk_run_status to observe the returned run and request bounded cursor-addressed run or gate logs. Use hk_run_cancel only for the intended exact observed active run.
Run and Observe
- Inspect
hk_contextand known run status for equivalent active QA work before starting another. - Persist a source-bound plan with
hk_qa_plan, then pass its requiredplan_idtohk_run_start. Use a structured CLI action with--detach --output jsononly after the MCP blocker has been reported and the user has approved fallback. Keep the returned workspace ID and run ID. - Poll
hk_run_statusrather than restarting a slow run or assuming client disconnect stopped it. - On failure, request the bounded run tail, then a bounded gate-specific view from
hk_run_status. Open the complete local artifact only when that context is insufficient. - Fix the root cause and rerun the smallest relevant selection from the live catalog before rerunning the required profile.
- Let all selected gates finish; one failure must not hide independent results. Cancel only the intended validated run.
What ships with it
1 file 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.
- 1mo ago Changed · +4 lines c01133dcf045
- 1mo ago First seen · 37 lines · 57 tokens per session scan A 91ced3a9c4ce
hitkeep-qa is a skill published in the GitHub repository PascaleBeier/hitkeep (98 stars, last pushed 4d ago), licensed MIT. It adds 57 tokens to every session and 713 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 2026-08-30.
Other skills, from other repositories
code-guidelines-go
Go 1.24–1.27 coding guidelines for the dimetron/pi-go AI agent runtime. Use this skill whenever writing, reviewing, or refactoring ANY Go code in pi-go. This covers idiomatic style, error handling, concurrency, project layout, testing (table-driven, fuzz, benchmarks, synctest), new stdlib usage, golangci-lint v2…
go-127
What changed in Go 1.27 (released August 2026) and how it changes the way Go is written in pi-go. Use this skill when writing or reviewing Go that could use a 1.27 feature, when bumping the go directive in go.mod, when a build or test behaves differently after a toolchain upgrade, or when code-guidelines-go points…
bubbletea-testing
Use this skill whenever writing tests for Bubble Tea (charmbracelet/bubbletea) TUI applications in Go. Triggers include any mention of testing Bubble Tea models, teatest, golden file testing for TUIs, testing tea.Cmd or tea.Msg, snapshot testing terminal output, or writing tests for any Go CLI/TUI that uses the Elm…
auditing-experiments-flags
Audit PostHog experiments and feature flags for configuration issues, staleness, and best-practice violations. Read when the user asks to audit, health-check, or review experiments or feature flags, check flag hygiene, or verify experiment setup.
vhs-e2e-gif
Record a test run, a TUI session, or any terminal command as a GIF with VHS and attach it to a GitHub PR as a release-hosted asset, never a repo commit. Use when asked to record an e2e run, demo a fix on a PR, attach a GIF or screen recording to a pull request, show a test passing visually, or produce a terminal…
email-evals
Author and safely run deterministic email-agent evaluation suites with dedicated e2a test agents. Use when a user wants to define synthetic email cases, validate a suite, inspect its dry-run plan, run it after approval, or regrade changed assertions.