workflows

A set of reusable workflows for finding developers and collaborators using public evidence, then involving the user before any introduction. It runs through the DevGlobe server, a service for developer discovery.

In plain words
What is it for?
Use it to find developers by skill, role, language, location, or contribution activity. It can also find collaborators or a contribution-ready GitHub issue for a specific account.
Why use it?
It helps avoid unsupported guesses about people’s skills or availability and keeps contact decisions under the user’s control.

Agent

Install

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.

agentmods
npx agentmods add agents/sajeetharan/devglobe/workflows
Clone the repo
git clone --depth 1 https://github.com/sajeetharan/devglobe
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 616 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00017 $0.00616
Opus 5 $0.00009 $0.00308
Sonnet 5 $0.00003 $0.00123
Haiku 4.5 $0.00002 $0.00062

Measured yesterday against content hash 1bcbf89f75ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workflows 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 yesterday.

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.

docs-site/agents/workflows.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent workflows

These recipes keep discovery grounded in public evidence and leave contact decisions with the user and developer.

Clients with MCP prompt support can select these workflows directly from the DevGlobe server:

Prompt Use it for
find-developers Skill, language, role, or location-based discovery
find-collaborators Developers with active self-declared opportunity availability
find-contribution One contribution-ready issue for an indexed GitHub login

Find relevant experts

Find three TypeScript maintainers in Canada. Explain why each profile matched and cite only public contribution evidence.

The agent should call search_developers, then use get_developer_profile only when more detail is needed.

MCP prompt example: select find-developers, set criteria to TypeScript maintainers, and set location to Canada.

Start with a repository

Find developers relevant to sajeetharan/devglobe and explain each match using public evidence.

Call match_developers_to_repository with the public GitHub owner/repository. Repository ownership and public contribution history are stronger signals than language and topic affinity. Returned ordering is a discovery aid, not a hiring or suitability recommendation.

Find agent-ready developers

Find Python developers who currently accept requests from verified agents.

Set availableForAgents to true. Availability is developer-controlled and does not imply acceptance of a specific request.

MCP prompt example: select find-collaborators, set criteria to Python, and set opportunityType to open-source.

Find a contribution

Select find-contribution with an indexed GitHub login. The workflow calls preview_contribution_mission, explains the public match reasons, and reminds the user that previewing does not reserve the issue.

Compare public evidence

Compare the public open-source signals for these two developers. Explain data freshness and do not make a hiring recommendation.

Read the full file on GitHub · 63 lines

Changes

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.

  1. yesterday First seen · 63 lines · 17 tokens per session scan A 1bcbf89f75ce

Subscribe to this mod's changes

workflows is an agent published in the GitHub repository sajeetharan/devglobe (31 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 616 once invoked, about $0.0001 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.

Related

Other agents, from other repositories