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 jscraik/Agent-Skills --skill devrel-hack-coachgit clone --depth 1 https://github.com/jscraik/Agent-SkillsWrote 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/jscraik/agent-skills/devrel-hack-coach)<a href="https://agentmods.dev/skills/jscraik/agent-skills/devrel-hack-coach"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/devrel-hack-coach/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/jscraik/agent-skills/devrel-hack-coach"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/devrel-hack-coach.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 | $0.00078 | $0.02342 |
| Opus 5.5 | $0.00031 | $0.00937 |
| Sonnet 5.5 | $0.00016 | $0.00468 |
| Haiku 4.5 | $0.00008 | $0.00234 |
Grade A, and why
devrel-hack-coach 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 1mo 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevRel Hack Coach
Move an engineer from vague hackathon itch to locked spec, timeboxed plan, and three-sentence demo pitch. Support 1-hour prep to 24-hour builds. Keep it short.
When To Use
Use this skill when the user is shaping a hackathon project, pitch, demo, or track decision. Keep the work at coaching altitude: idea pressure test, spec, timebox, scope cuts, pitch, and judge Q&A.
First-response trigger: when the user asks which track fits, says they do not know the track, or asks you to pick a track, recommend one track before any question. For context-loss, retrieval, or grounding itches, pick Context Engineering, give the reason, offer a veto, then ask for stack.
Do not use it for code generation, file layout, pair-programming, event logistics, travel, ticketing, or general DevRel strategy.
Inputs
Gather one input per turn: stack, track or track preference, one named itch, missing spec fields, checkpoint artifacts, and grounded decisions so far.
Outputs
Deliver hack angles, spec, checkpoints, pitch, Q&A, state map, a consolidated hackathon spec-and-plan artifact, and stop message.
Workflow
Run the phases in order. Each phase narrows the next one. Announce each phase as "OK, Phase N - ." Do not skip ahead. Track-choice answers are Phase 1 work, not a phase skip. Loop inside a phase until its exit gate is met.
Keep a grounded-state map because a later artifact can only lean on decisions the user has already made. Track stack, track, itch, selected angle, demo moment, scope cuts, checkpoint artifacts, real-vs-mocked boundary, artifact status, and pitch wedge. If the next move needs an ungrounded decision, ask for that decision before writing the artifact.
Non-negotiable overrides:
- Track choice: if the user asks which track fits or says they do not know the track, do not lead with the stack question. Pick one track with a reason, offer a veto, then ask for stack.
- Locked-spec planning: if the user says the spec is locked and asks for a 24-hour plan, name T+2h, T+8h, T+16h, and T+22h checkpoint artifacts before asking for missing spec details.
What ships with it
32 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 229 B
- README.md 929 B
- references/coaching-style.md 745 B
- references/contract.yaml 13 KB
- references/devcon-tracks.md 3.3 KB
- references/devrel-hack-coach-hackathon-workflow.md 3.1 KB
- references/devrel-hack-coach-ideation-pressure-test.md 3.1 KB
- references/devrel-hack-coach-one-hour-five-minute-software-presentation.md 4.0 KB
- references/devrel-hack-coach-pitch-and-judge-qa.md 2.9 KB
- references/devrel-hack-coach-scope-cutting.md 2.8 KB
- references/devrel-hack-coach-spec-first-demo.md 2.8 KB
- references/devrel-hack-coach-track-aware-selection.md 2.7 KB
- references/devrel-hack-coach-twenty-four-hour-plan.md 2.6 KB
- references/evals.yaml 27 KB
- references/example-quality-bars.md 410 B
- references/examples/good-pitch.md 1.3 KB
- references/examples/good-spec.md 1.6 KB
- references/hackathon-spec-plan-artifact.md 4.2 KB
- references/knowledge-capsule-routing.md 2.3 KB
- references/knowledge-capsule.manifest.yaml 3.4 KB
- references/knowledge-demand.yaml 1.3 KB
- references/pitch-template.md 1.4 KB
- references/scorer-calibration/examples.jsonl 357 B
- references/scorer-calibration/manifest.json 638 B
- references/scorer-calibration/raw/obvious-correct-phase-gate.json 232 B
- references/scorer-calibration/raw/obvious-wrong-code-first.json 229 B
- references/source-context.yaml 5.6 KB
- references/source-provenance.md 697 B
- references/spec-template.md 1.3 KB
- references/task-profile.json 1.6 KB
- references/timebox-plans.md 1.0 KB
- references/validation-and-output.md 1.5 KB
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.
- 1mo ago First seen · 230 lines · 78 tokens per session scan A e38b8a926bca
devrel-hack-coach is a skill published in the GitHub repository jscraik/Agent-Skills (9 stars, last pushed 4d ago), licensed Apache-2.0. It adds 78 tokens to every session and 2,342 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 2026-09-13.
Other skills, from other repositories
agui-dotnet-streaming-chat
Get started with the AG-UI .NET SDK: bootstrap and run your first streaming-chat app (client + server) with the AG-UI .NET NuGet packages (AGUI.Client, AGUI.Server, AGUI.Formatting, AGUI.Abstractions). USE FOR: which packages to install and how to wire them; constructing an AGUIChatClient against an endpoint and…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.