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 agentmods add skills/hon454/grimoire/issue-preflightnpx skills add hon454/grimoire --skill issue-preflightgit clone --depth 1 https://github.com/hon454/grimoireWrote 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/hon454/grimoire/issue-preflight)<a href="https://agentmods.dev/skills/hon454/grimoire/issue-preflight"><img src="https://agentmods.dev/badge/skills/hon454/grimoire/issue-preflight.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.02869 |
| Opus 5 | $0.00017 | $0.01435 |
| Sonnet 5 | $0.00007 | $0.00574 |
| Haiku 4.5 | $0.00003 | $0.00287 |
Grade A, and why
issue-preflight 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 4d 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 — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue Preflight
Audit work-item validity before implementation, then stop. The goal is to prevent unnecessary or mis-scoped implementation by grounding tracker claims in current code, docs, tests, linked changes, and branch freshness.
Use only when explicitly invoked as $issue-preflight or "use the issue-preflight skill".
Output Locale
Resolve the final-output locale before inspecting sources. Prefer output
values from the Grimoire session config cache created by the Grimoire
SessionStart hook. Treat the cache file, not hook stdout, as the session
config source of truth. Hook stdout may help locate the cache path, but it is
only diagnostic.
When the cache is available, use output.locale from the cached session config
and include output.locale_source in the locale notice. If no Grimoire session
config cache is available, continue by directly observing the host OS preferred
locale with deterministic local signals and note the missing session config
only if it changes confidence.
If the user explicitly requests a final-output locale with a valid locale tag, pass it as an explicit override to the Grimoire config resolver when available. The resolver does not interpret natural-language locale requests. If no valid locale tag is provided, use Grimoire session config or OS preferred locale detection. This is the only override. Do not infer the final-output locale from conversation prose, tracker text, this skill file, repository prose, tool output, copied templates, or quoted artifacts.
Include one short locale notice before the source notice. State the resolved locale and whether it came from session config, explicit override, or direct OS observation. If the host supports interim messages, send it before inspection; otherwise make it the first line of the final response.
Use the resolved locale for user-facing prose, including notices, section headings, labels, rationale, evidence summaries, next action, and the tracker draft. Preserve issue IDs, PR numbers, branch names, commands, paths, and code identifiers as written after applying the data-handling rules below. Preserve decision taxonomy values as stable code values.
What ships with it
3 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.
- 4d ago First seen · 302 lines · 35 tokens per session scan A c1a20b1c0aff
issue-preflight is a skill published in the GitHub repository hon454/grimoire (2 stars, last pushed 15d ago), licensed MIT. It adds 35 tokens to every session and 2,869 once invoked, about $0.0002 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
triage
Apply a formal state machine to issues — assign category (bug/enhancement/question/spike) and state (needs-triage → needs-info → ready-for-agent → ready-for-human → wontfix). Issues marked ready-for-agent become inputs to supergraph:plan. Use when processing a backlog, reviewing new issues, or preparing work for…
frappe-gameplan
Frappe Gameplan guidance for team discussions, projects, tasks, notes, decisions, async collaboration, permissions, and workspace workflows. Use when work touches Gameplan or planning/collaboration features in the Frappe ecosystem.
geo-prospect
CRM-lite for managing GEO agency prospects and clients. Track leads through the full sales pipeline: Lead → Qualified → Proposal Sent → Won → Lost. Store audit history, notes, deal values, and generate pipeline summaries. Use when user says "prospect", "lead", "client", "pipeline", "crm", "nuovo prospect", "aggiungi…
note-improvement
Capture an out-of-scope improvement opportunity so it doesn't get lost. Use when the user asks to "note improvement", "save improvement", "track this for later", "remember this improvement", "note this idea", "log improvement", "backlog this", or "park this idea". Also invoke proactively when noticing something…
implement
Load code-style and task-specific skills, make the change described by the current context, then run post-implementation QA. Use for ad-hoc changes when no plan file or improvements backlog governs the work, and when the user asks to "just implement", "implement directly", "implement without a plan", or "apply the…
harness-design
Design and build multi-agent harness architectures for long-running AI application development. GAN-inspired Generator-Evaluator pattern, Sprint Contract negotiation, context management, quality criteria calibration. Based on Anthropic Engineering patterns. Use when: "build a harness", "multi-agent architecture"…