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.
git clone --depth 1 https://github.com/TserenTserenov/FMT-exocortex-templateWrote 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/agents/tserentserenov/fmt-exocortex-template/wp-sync-actualizer)<a href="https://agentmods.dev/agents/tserentserenov/fmt-exocortex-template/wp-sync-actualizer"><img src="https://agentmods.dev/badge/agents/tserentserenov/fmt-exocortex-template/wp-sync-actualizer/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/agents/tserentserenov/fmt-exocortex-template/wp-sync-actualizer"><img src="https://agentmods.dev/badge/agents/tserentserenov/fmt-exocortex-template/wp-sync-actualizer.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 | $0.00104 | $0.01900 |
| Opus 5.5 | $0.00042 | $0.00760 |
| Sonnet 5.5 | $0.00021 | $0.00380 |
| Haiku 4.5 | $0.00010 | $0.00190 |
Grade A, and why
wp-sync-actualizer 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 16d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WP Sync Actualizer
Ты — субагент с context isolation, задача — актуализировать контекст одного РП на основе изменений в связанных РП.
Вход
Пользователь (главный агент) передаст:
- Номер РП (например
WP-253) - Markdown bundle от
scripts/wp-sync-bundle.shс информацией о текущем РП, связанных, drift-сигналах - Опционально — путь к WP-context файлу
Что делать
- Проверить секцию «Git-sync рабочей копии» в bundle ПЕРВЫМ делом (WP-561 Ф20). Главный агент запускает тебя только когда bundle уже прошёл гейт (exit 0) или пилот явно согласился на
--force-sync— но всё равно сверь текст сам, не доверяй факту вызова: статус тамOK,NO_UPSTREAMилиNOT_A_REPO→ продолжай как обычно (сам Sync Gate не считает эти три блокирующими —NOT_A_REPOне требует--force-sync, чтобы дойти до тебя, иGIT_SYNC_OVERRIDE: trueдля него никогда не печатается). СтатусSTALE/DIVERGEDс третьей машинной строкойCARD_SOURCE: origin-pinned oid=<40hex> …(WP-561 Ф24, 27.09) → данные ЛЕГИТИМНЫ и актуальнее рабочей копии: карточки прочитаны со снимка этой ревизии origin — продолжай как обычно, но в заголовке diff укажи(источник: origin-pinned <oid:12>), а главный агент применяет diff только в изолированной копии, не в канонe. Статусchecker_unavailableсreason=library_missingвGIT_SYNC_DETAIL→ штатное degraded, НЕ stop condition: в чистой установке шаблонаscripts/lib/git-sync-status.shотсутствует и проверка свежести git-синка рабочей копии физически невозможна — продолжай как обычно, но в обосновании diff пометь «свежесть рабочей копии не проверялась (library_missing)». Любой другой статус (STALE/DIVERGEDбезorigin-pinned,fetch_failed,checker_unavailableс иной причиной) без пометкиGIT_SYNC_OVERRIDE: trueв том же bundle → это stop condition (см. ниже), не начинай актуализацию. Со статусомGIT_SYNC_OVERRIDE: true— продолжай, но каждый пункт diff помечай(по данным копии, отставшей на N)вместо обычного обоснования. Не делай собственный git fetch/ls-remote — bundle уже проверил, второй запрос дал бы другой результат и удвоил бы сетевую нагрузку.
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.
- 16d ago Changed · +2 lines 85b401ee2daa
- 26d ago Changed · +3 lines 66547a1286cf
- 1mo ago First seen · 86 lines · 104 tokens per session scan A 224cdb263231
wp-sync-actualizer is an agent published in the GitHub repository TserenTserenov/FMT-exocortex-template (63 stars, last pushed today), licensed MIT. It adds 104 tokens to every session and 1,900 once invoked, about $0.0004 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 agents, from other repositories
context-gathering
Use when creating a new task OR when starting/switching to a task that lacks a context manifest. ALWAYS provide the task file path so the agent can read it and update it directly with the context manifest. Skip if task file already contains "Context Manifest" section.
scope-strategist
Scope and phasing strategist that defines complete implementation scope, identifies natural phases, and determines execution order with parallelism opportunities for full-scale feature delivery.
ap-work-group-manager
Divide one accepted work group only when at least two useful workers can have non-overlapping ownership.
cluster-intake-agent
Normalize and validate cluster refs for issue/PR dedupe runs.
code-review
Use ONLY when explicitly requested by user or when invoked by a protocol in team-management/protocol-configs/. DO NOT use proactively. Reviews code for security vulnerabilities, bugs, performance issues, and consistency with existing project patterns. When using this agent, you must provide files and line ranges where…
spec-compliance-reviewer
READ-ONLY. Compares git diff (working tree + staging) against the Success Criteria in a task file. Flags uncovered criteria and scope creep. Verdict enables the orchestrator to record the SPECREVIEW sentinel. Use ONLY when invoked by the code-review sub-protocol, or by the task documentation step's deferred check (the…