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-integrationsgit 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-integrations)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/work-integrations"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/work-integrations/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-integrations"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/work-integrations.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 | $0.00604 |
| Opus 5.5 | $0.00017 | $0.00242 |
| Sonnet 5.5 | $0.00009 | $0.00121 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
work-integrations scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 26d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crew integrations
Inspect current state before changing it, and distinguish account-level setup
from selection for this project. MCP setup has its own work-mcp skill.
Secrets
- Call
list_secretsbefore creating, replacing, or deleting a secret. set_workflow_secretanddelete_workflow_secretmanage project-scoped secrets in Crew (legacy tool names for the shared project store). There is no account-level secret: a credential shared across projects must be a global, promoted by an administrator (see below).- After
set_workflow_secretsucceeds,$SECRET_<NAME>is available to shell tools immediately in the current chat and remains available in later turns. Continue the requested work in the same chat; do not ask the user to start a new chat or session. Verify availability without printing the secret value. - Work stores attached secret names in
workflow.jsonundercapabilities.selected_secrets, using the AgentWorks workflow contract. Secret values remain encrypted outside the manifest. Respect the user's selections in Setup > Secrets; do not attach an unrelated credential. - A read-only workflow or Crew reference never grants its secrets. To reuse a
credential across projects, an administrator must explicitly promote the
source project/workflow secret with
manage_global_secret(action="promote")or Make global in Setup > Secrets. Then explicitly select that global name in each destination Crew withupdate_project_global_secret_selection(action="select", name="NAME"). Calllist_secretsfirst and use an exact name fromglobal.names. Crew persists this allowlist incapabilities.selected_global_secret_names; it never inherits newly created globals automatically. - Never print, echo, store in project files, or otherwise reveal a secret value. Refer to secrets by name.
Attached folders
- Use
list_work_foldersfirst. Attach only an existing path permitted by the administrator, with a clear alias and the least access needed (read_onlyunless writes are required). - Use the exact stored ID when detaching. A newly attached folder becomes part of the native CLI guard on the next turn; do not pretend the current turn's process gained access retroactively.
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.
- 26d ago Changed · +1 lines ff371ac500d5
- 28d ago Changed · +9 lines 98d675552470
- 1mo ago Changed · -6 lines · -13 tokens per session 7be61d35c87c
- 1mo ago First seen · 49 lines · 56 tokens per session scan A 7b155b7346c6
work-integrations is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 43 tokens to every session and 604 once invoked, about $0.0002 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
goga-cell-go
Golang rules for implementing CODEMANIFEST contracts.
faq-mine
Mine docs/faq.md from README.md, docs/.md, and the pi-hermes memory stores. Dispatches @fast subagents per source, dedupes against the existing FAQ, and merges entries in caveman style. Use when asked to "build / regenerate / extend the FAQ", "mine docs into FAQ", "mine hermes memory into FAQ", "surface runtime…
autofix
Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewer-provided prompts directly.
node-inspect-debugger
See runtime state a console.log cannot reach — set real breakpoints, step, and dump the scope chain of a paused Node/TypeScript process. Use on "set a breakpoint", "inspect runtime state", "console.log isn't enough", "step through this", "what's in this closure at runtime", "attach a debugger". Not a logging or…
browser
Browser automation via the agent-browser CLI. Use when the user needs to drive websites or Electron apps — navigating, forms, clicks, screenshots, data extraction, testing web apps, UI checks, the dashboard Electron shell, or the user's own logged-in Chrome via the browser relay or Panerelay (SSO/2FA). Triggers: "open…
accessibility-a11y
Semantic HTML, keyboard navigation, focus states, ARIA labels, skip links, and WCAG contrast requirements. Use when ensuring accessibility compliance, implementing keyboard navigation, or adding screen reader support.