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 Jessinra/Lorekeeper --skill github-app-bot-authgit clone --depth 1 https://github.com/Jessinra/LorekeeperWrote 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/jessinra/lorekeeper/github-app-bot-auth)<a href="https://agentmods.dev/skills/jessinra/lorekeeper/github-app-bot-auth"><img src="https://agentmods.dev/badge/skills/jessinra/lorekeeper/github-app-bot-auth/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/jessinra/lorekeeper/github-app-bot-auth"><img src="https://agentmods.dev/badge/skills/jessinra/lorekeeper/github-app-bot-auth.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 | $0.00031 | $0.01510 |
| Opus 5.5 | $0.00012 | $0.00604 |
| Sonnet 5.5 | $0.00006 | $0.00302 |
| Haiku 4.5 | $0.00003 | $0.00151 |
Grade A, and why
github-app-bot-auth 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub App Bot Auth — jessinra-megumi-dev[bot]
What This Is
The Lorekeeper ecosystem uses a GitHub App (jessinra-megumi-dev) for bot-authorized gh operations — PR creation, code pushes, API calls. The bot identity is separate from Jason's personal account, giving cleaner audit trails on PRs.
Key Facts
| Item | Value |
|---|---|
| App ID | 3823074 |
| Installation ID | 134866394 |
| Account | Jessinra (User, selected repos) |
| Bot display name | jessinra-megumi-dev[bot] |
| Private key | ~/.hermes/keys/jessinra-megumi-dev.private-key.pem |
| Auth file | ~/.config/gh/hosts.yml |
| Token prefix | ghs_ (installation token) |
Authentication Flow
Private Key (.pem)
→ Sign JWT (RS256, App ID 3823074, 10min expiry)
→ POST /app/installations/134866394/access_tokens
→ Installation token (ghs_..., 1hr expiry)
→ Written to ~/.config/gh/hosts.yml
Token Rotation
Installation tokens expire in 1 hour. A cron job refreshes them automatically:
- Script:
~/.hermes/scripts/gh-token-refresh.py - Schedule: Every 45 minutes (
*/45 * * * *) - Mode:
no_agent=True(pure script, no LLM cost) - Delivery:
local(silent — no Telegram spam)
The script:
- Reads the PEM key from
~/.hermes/keys/jessinra-megumi-dev.private-key.pem - Generates a JWT signed with RS256 (PyJWT preferred, falls back to
openssl dgst -sha256 -sign) - Exchanges for an installation token via GitHub API
- Writes
~/.config/gh/hosts.ymlwith the fresh token inline - Pushes the token into gh's keyring via
gh auth login --with-token(withGH_TOKEN/GITHUB_TOKENunset) - Verifies
gh auth tokenresolves a validghs_token
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 First seen · 132 lines · 31 tokens per session scan A cd2d08ef9933
github-app-bot-auth is a skill published in the GitHub repository Jessinra/Lorekeeper (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 1,510 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
merge-strategy
Git merge strategies, conflict resolution approaches, merge vs rebase recommendations, and branch integration patterns in sidecar. Covers pull strategy menu, direct merge workflow, squash merge, commit message templates, configurable defaults, and protected branches. Use when working on git merge features or making…
worktree-switching
Git worktree support in sidecar: worktree detection, switching between worktrees, worktree state management, and plugin reinitialization. Covers the full lifecycle of worktree context switching including registry reinit, per-worktree state persistence, deleted worktree detection and fallback. Use when working on git…
release-sidecar
Release new versions of sidecar. Covers version tagging with semver, td dependency updates, go.mod validation, CHANGELOG updates, GoReleaser automation, Homebrew tap updates, and verification steps. Use when preparing or executing a release.
pre-pr
Prepare a Honcho change for a pull request to plastic-labs/honcho. Invoke before opening a PR, when drafting a PR body, when asked if a branch is PR-ready, or when filling the pull request template. Checks the linked issue, required tests and docs, then writes Description / Proofs / Fixes.
commitlore-commits
Use when about to make a git commit and there is decision context worth recording — a constraint that shaped the change, an alternative that was tried and dropped, a warning for whoever touches this next. Drives the CommitLore capture pipeline, which drafts a record from the session transcript and the staged diff…
commitlore-query
Use when about to read, edit, or reason about a file and it would help to know its recorded decision history — active constraints, alternatives already ruled out, warnings left by a previous author, or which records have gone stale. Reads CommitLore records for a path or the whole repo without re-deriving them from…