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/elanthus/agentic-preflight/skillnpx skills add elanthus/agentic-preflight --skill skillgit clone --depth 1 https://github.com/elanthus/agentic-preflightWrote 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/elanthus/agentic-preflight/skill)<a href="https://agentmods.dev/skills/elanthus/agentic-preflight/skill"><img src="https://agentmods.dev/badge/skills/elanthus/agentic-preflight/skill.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 | $0.00066 | $0.04491 |
| Opus 5 | $0.00033 | $0.02246 |
| Sonnet 5 | $0.00013 | $0.00898 |
| Haiku 4.5 | $0.00007 | $0.00449 |
Grade A, and why
agentic-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 3d 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 — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentic-preflight
You review, judge, and fix. The CLI holds all state and tells you what to do next. Python here never calls a model — every judgment in this workflow is yours.
Non-negotiables
- You think, the CLI holds state. Never guess where a run is. Ask
status. - Parse stdout as JSON and obey
next. Every agent-facing workflow command prints exactly one JSON object.hook-checkis the sole exception because Git, not you, consumes its exit status and stderr.next.commandis the single next legal move. Follow it. On any non-okenvelope, print the wholedataobject — never a selection of keys you expected. Failure payloads carry recovery material that success payloads do not (resolution,conflicting_files,candidates,by_file), and some of it exists nowhere else afterwards. - Never invent code-assigned finding fields. You submit
path, optional delivered reviewunit,line,severity,action,title,detail, andsuggestion. Sendingid,stage, orcode_ownedis a hard validation error, not a nudge. - Never run
git push --no-verify. It exists for humans, not for you. - Never push without user authorization. An explicit request to push, publish, or
create/open a pull request authorizes the matching push in that task; after
gate, show what will be pushed and proceed without asking a second time. If publication was not explicitly requested, or the remote, branch, commits, or risk summary is materially different from what the user authorized, show the summary and wait for an actual answer. A generic request to implement, commit, or "proceed" is not push authorization.[pr] mode = "auto"is standing authorization to open or reuse the pull request after the authorized push and preflight finish. Withmode = "manual", never open the PR for them. - Never resolve a merge-back conflict. Paste the resolution block and stop.
- Keep the validation checkout clean for the whole run. The default
in_placemode uses the current checkout, so only deliberate repair commits may move its branch; uncommitted changes or an unaccounted commit stop the run..agentic-preflight.tomlmust be committed beforestartand must not be edited mid-run. Inreusableorstrictmode, make repairs only in the absoluteworktree_pathreturned by the CLI. - Never merge a high-risk
manual_mergepull request or enable auto-merge. The hosted check fails while auto-merge is enabled; when successful, it records that the user must perform the merge and is not authorization for the agent to merge.
What ships with it
4 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.
- 3d ago First seen · 343 lines · 66 tokens per session scan A 139f56fdfa77
agentic-preflight is a skill published in the GitHub repository elanthus/agentic-preflight (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 66 tokens to every session and 4,491 once invoked, about $0.0003 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
lorekeeper-dev-self-review
Mandatory Reflexion self-review loop for all Lorekeeper devs before pushing or opening PRs. Actor → Evaluator → Reflector cycle (max 3 iterations). Every dev must run this before git push.
review-work
Quality gate: verify each acceptance criterion of a completed task/work unit, run quality checks, and create follow-up tasks for gaps. Use before merging or to audit delivered work. Invoked as /agiflow:review-work . Uses getworkunit, gettask, updatetask, createtask, createtaskcomment.
dos-verify-done-claims
Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's dos verify and dos commit-audit — never the agent's own narration.
tighten
偵測並重寫 Markdown 的冗贅用詞。純 regex 先掃 10 條 bloat pattern，再用 sonnet sub-agent 重寫 flagged 段落。觸發：「幫我精簡」「砍冗贅」「tighten」 「檢查用詞」「token 節省」，或呼叫 /tighten [paths]。.
tsq-tidying
구현 완료 후 필수 실행되는 코드 정리 + AI 안전 검증 게이트. Deep Module 준수, Tidying First 분리, glossary 네이밍 검증, 보안 스캔을 강제한다. tsq-developer가 "구현 완료"를 선언하기 전에 반드시 이 스킬의 Protocol을 통과해야 함. Use when: 구현 완료 직전, PR 전, 코드 리뷰 전, "tidying", "정리", "코드 품질 검증".
evidence-calibration-review
Use when you want a per-claim evidence-tier audit on a text artifact before it ships — assign T1-T6 tiers to every load-bearing claim, surface calibration mismatches (high confidence on weak evidence, or honesty-theater under-claiming), and flag P11 (citation-as-decoration), P17 (pile-of-anecdotes-as-evidence), P54…