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 manishiitg/coding-agent-loop --skill work-workflow-filesgit clone --depth 1 https://github.com/manishiitg/coding-agent-loopWrote 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/manishiitg/coding-agent-loop/work-workflow-files)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/work-workflow-files"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/work-workflow-files/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/manishiitg/coding-agent-loop/work-workflow-files"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/work-workflow-files.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 | $0.00084 | $0.02523 |
| Opus 5.5 | $0.00034 | $0.01009 |
| Sonnet 5.5 | $0.00017 | $0.00505 |
| Haiku 4.5 | $0.00008 | $0.00252 |
Grade A, and why
work-workflow-files 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 19d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use attached workflows
Share an active Crew project file or folder
For the project's live Dashboard, call get_report_link with no arguments and
use its returned url. Do not pass db/reports/index.html to get_file_link:
that would open a restricted generic HTML preview instead of the full Dashboard
runtime, and the file-link tool rejects that Dashboard entry path. The dedicated
Dashboard URL renders the Dashboard full-page and uses the normal AgentWorks SSO;
do not add a separate publish password or login to this internal URL. Publicly
hosted static Dashboards remain a separate publish flow with their own visibility
controls.
Call get_file_link with the path relative to the active Crew project. The
server verifies that the target exists, rejects private or escaping paths,
detects file versus folder, and returns the correct authenticated
preview_url. Never construct /file or /folder URLs manually.
Always inspect shareable, scope, and warning in either link tool's result.
If shareable is false, tell the user it is only a same-machine preview and
include the warning; do not call it a shareable link. A URL based on localhost,
127.0.0.1, or ::1 cannot be opened by another user or device. The deployment
must have a reachable PUBLIC_URL before the link can be shared.
Crew projects are personal. The URL contains no credentials and grants no access; it can currently be opened only by the same signed-in Crew account. Do not describe it as public publishing or as a way to grant another user access. Use a publishing workflow when the user explicitly needs public or cross-user distribution.
Resolve the authorized root before reading:
- For an AgentWorks workflow or another Crew reference, use the exact path
supplied in attached context.
list_accessible_workflowsreturns separateworkflowsandcrewslists; every entry includes its projectnameand displayidentity(nameandicon), and each Crew also itsowner. Crews are shared: any Crew on the server can be attached. Use the exact returned path; never guess a project path or scan unattached projects. - For a host folder, call
list_work_foldersand use its$WORK_FOLDER_<ALIAS>variable. Do not inspect the parent directory. - Workflow references and host folders are read-only unless a host-folder
grant explicitly says
read_write. Never edit a referenced workflow. Execution is allowed only through the trigger procedures below. - Crew references (tagged or attached, any owner) are read-write: you may edit another Crew's files when the user asks, as you would your own.
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.
- 19d ago Changed · +2 lines 9169a0127556
- 22d ago Changed · +46 lines 0229994fbaf6
- 23d ago Changed · +26 lines 5d0133c334a4
- 25d ago Changed · +29 lines · +13 tokens per session 331248ee05d7
- 28d ago Changed · +3 lines 85a662b5bf7c
- 29d ago Changed · +1 tokens per session deaff551632a
- 1mo ago Changed · +15 lines 68d28f8d4e04
- 1mo ago First seen · 68 lines · 70 tokens per session scan A ee730a59a2dc
work-workflow-files is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 84 tokens to every session and 2,523 once invoked, about $0.0003 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 2026-09-15.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
material-organizer
Organize only the materials the user has already provided or explicitly pointed to. The job is to make messy inputs easier to scan, reuse, archive, or continue from later while preserving source traceability.
kungfu-agent-onboarding
Use when a user asks to understand, start, inspect, extend, or safely operate installed Kungfu; verify the installed pack, select one intent route, personalize the explanation, and propose one smallest safe next action.
pdfcraft
Headless PDF work with PdfCraft, provisioned on demand by pi-craft - combine, split, extract, rotate, delete and reorder pages, read text, render a page to png, audit faux redactions, script its 163 tools. Use for "merge these two PDFs", "extract pages 1 and 3 from this PDF", "rotate page 1 and drop page 2", "what…
pdf-processor
Extracts text and tables from PDF files, fills forms, and merges documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.