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 agentmods add agents/sajeetharan/devglobe/workflowsgit clone --depth 1 https://github.com/sajeetharan/devglobeWhat 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 | $0.00017 | $0.00616 |
| Opus 5 | $0.00009 | $0.00308 |
| Sonnet 5 | $0.00003 | $0.00123 |
| Haiku 4.5 | $0.00002 | $0.00062 |
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.
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/devglobeand 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.
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.
- yesterday First seen · 63 lines · 17 tokens per session scan A 1bcbf89f75ce
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.
Other agents, from other repositories
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.
audit-creative
Cross-platform creative specialist. Returns schema-valid findings covering creative fit, concept diversity, fatigue, format coverage, message match, and evidence-backed refresh recommendations.
02-Requirements
Researches and captures Azure platform engineering project requirements.
d3-expert
Expert in D3.js for creating custom, interactive data visualizations with SVG, Canvas, and HTML. Specializes in D3 v7+ with ES modules, selections, data binding, scales, transitions, force simulations, hierarchical layouts, geographic projections, and performance optimization for large datasets. Use for any data…
stage-6-settlement
Agent "stage-6-settlement" from TelivityAI/otaip, covering stage 6 -- settlement agents, agent 6.1 -- refund processing, agent 6.2 -- adm prevention, agent 6.3 -- adm/acm processing and agent 6.4 -- customer communication.
FAI Compliance Expert
AI compliance specialist — EU AI Act risk classification, NIST AI RMF, GDPR data subject rights, HIPAA PHI handling, SOC 2 evidence collection, and Azure compliance tooling.