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 JiuNian3219/architext --skill archi-task-state-reconcilegit clone --depth 1 https://github.com/JiuNian3219/architextWrote 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/jiunian3219/architext/archi-task-state-reconcile)<a href="https://agentmods.dev/skills/jiunian3219/architext/archi-task-state-reconcile"><img src="https://agentmods.dev/badge/skills/jiunian3219/architext/archi-task-state-reconcile/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/jiunian3219/architext/archi-task-state-reconcile"><img src="https://agentmods.dev/badge/skills/jiunian3219/architext/archi-task-state-reconcile.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 | $0.00043 | $0.01123 |
| Opus 5 | $0.00022 | $0.00562 |
| Sonnet 5 | $0.00009 | $0.00225 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade A, and why
archi-task-state-reconcile 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 12d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invocation
- Auto invoke: No. Only invoked explicitly by
/archi.*protocols through[[SUBAGENT]]/[[NO-SUBAGENT]]. - Trigger location: A task is blocked by
pending/blocked/ deps not done, and stale status may be the cause. - Execution context: When subagents are supported, must run in an isolated subagent/context. Without subagents, fall back to inline Skill execution.
- Boundary: Only judge whether task status is stale and return a recommended action; never mutate roadmap/task status directly.
Architext Task State Reconcile
Purpose
Decide whether a task or dependency is actually complete/planned while roadmap status is stale. This Skill is a status reconciler; it does not implement, edit docs, or sign off for the main protocol.
Inputs
task_id: Task being checked.mode:dependency_done|target_activedependency_done: Check whether a dependency is actually complete and can be marked done.target_active: Check whether the target task has completed detail and can be marked active.
reason: Invocation reason, for exampleblocked_by_deps,target_pending.known_blockers: Blocker IDs known by caller, optional.
Read Budget
- Read only target task and direct deps from
global/roadmap.json, extractingid/title/status/deps. - Read
spec.mdandplan.jsonunder the target task directory; missing files mean insufficient evidence. - May run:
npx archi plan <ID>: judge plan completion / detail readiness.npx archi task --check: judge structure state has no ERROR.
- Check artifact existence only when plan explicitly lists key output paths. Do not read all source files.
- Do not read unrelated tasks, refs, screens, or large product source files.
Decision Rules
mode = dependency_done
Return status_stale_done only when all are true:
spec.mdandplan.jsonexist;- all AI-completable
plan.jsonitems are done, ornpx archi plan <ID>reports complete / only exempt items remain; npx archi task --checkhas no ERROR;- if plan declares key artifact paths, those paths exist.
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.
- 12d ago First seen · 108 lines · 43 tokens per session scan A 7ca5a8676a02
archi-task-state-reconcile is a skill published in the GitHub repository JiuNian3219/architext (14 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 1,123 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 2026-08-30.
Other skills, from other repositories
ppt-orchestrator
A dispatcher for creating presentations, slide decks, long images, and weekly reports. It chooses a visual style and output format, then sends the work to a more specialised add-on.
zhongguose-html-skill
An HTML-only presentation system using traditional Chinese colours and Chinese-style visual design. It helps organise source material into a report structure and produces a self-contained HTML file with its assets.
dashiai-ppt
A presentation-making add-on that creates an HTML slide deck from preset visual page designs. The result can open offline in a browser and can be exported as a PowerPoint or PDF file.
wechat-delivery
A workflow for preparing WeChat Official Account articles, images, covers, and publishing files in Chinese. WeChat Official Accounts are channels used by organizations to publish articles to followers.
教程类H5-小红书小工具
A method for building offline, single-page course experiences for Xiaohongshu’s Mini Tools, which are interactive pages published inside the platform. It combines written lessons, generated illustrations, and JavaScript page switching in a constrained container.
huashu-book-pdf
A workflow for researching, planning, writing, reviewing, and building a complete book or guide as PDF, DOCX, and EPUB files.