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 skills/redhat-developer/rhdh-skills/rhdh-forgenpx skills add redhat-developer/rhdh-skills --skill rhdh-forgegit clone --depth 1 https://github.com/redhat-developer/rhdh-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/redhat-developer/rhdh-skills/rhdh-forge)<a href="https://agentmods.dev/skills/redhat-developer/rhdh-skills/rhdh-forge"><img src="https://agentmods.dev/badge/skills/redhat-developer/rhdh-skills/rhdh-forge.svg" alt="Measured on agentmods" 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 | $0.00140 | $0.01850 |
| Opus 5 | $0.00070 | $0.00925 |
| Sonnet 5 | $0.00028 | $0.00370 |
| Haiku 4.5 | $0.00014 | $0.00185 |
Grade A, and why
rhdh-forge 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 6d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RHDH Forge
One home for reading a forge and constructing its write payloads. Issue parsing,
issue fetch, workspace resolution, check and pipeline reads, repository content
reads, and the gh and glab behaviours that mislead a caller who has not met
them before all live here. Otherwise, every skill that touches a forge keeps its
own drifting copy.
This skill reads. It never executes a write.
GitHub work runs through gh. GitLab work — rhidp/rhdh and
rhidp/rhdh-plugin-catalog on gitlab.cee.redhat.com — runs through glab,
which is only needed when a GitLab host is in play.
Route by outcome
| Outcome | Load and follow |
|---|---|
| Turn a GitHub issue reference into structured context | Run uv run scripts/fetch_issue_context.py <reference> |
| Parse a GitHub or GitLab reference without a network call | references/issue-context.md |
| Resolve the plugin workspace an issue belongs to | references/issue-context.md |
| Read PR state, labels, assignees, files, or check status | references/gh-cli.md |
| Explain a failing, stale, or missing check | references/gh-cli.md |
| Read a file from a repository or a PR branch | references/gh-cli.md |
| Read a GitLab issue, MR state, pipeline status, or file | references/glab-cli.md |
| Prepare a GitHub pull-request creation payload | references/gh-cli.md, then the caller's mutation gate |
| Prepare a GitLab merge-request creation payload | references/glab-cli.md, then the caller's mutation gate |
Prepare a comment, label, assignee, or /publish payload |
references/issue-context.md, then the caller's mutation gate |
| Prepare a GitLab comment, label, or approval payload | references/glab-cli.md, then the caller's mutation gate |
Callers invoke this skill by name and consume what it returns. Do not load its files from another skill.
Invariants
- Every route here is read-only. A caller that needs a write gets a payload, not an execution.
- Construct an issue, PR, or MR URL from the resolved namespace, repository, and number. Never retain the user's raw URL; it may carry a fragment or a query string.
- A Jira key is not this skill's work. Extract it, hand it back, and let the
caller invoke
/rhdh-jira-apifor the detail. gh pr checksandstatusCheckRollupare cached views and go stale. Confirm a check verdict againstgh run list --branchbefore acting on it.- A GitLab pipeline verdict belongs to a commit, not to a merge request. Compare the pipeline's SHA against the MR head SHA before reporting it.
- Report an unresolved workspace as unresolved. Guessing one sends a caller into the wrong repository.
- Never read a credential file. If
gh auth statusorglab auth statusfails, stop and report the missing capability.
What ships with it
5 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.
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.
- 6d ago First seen · 153 lines · 140 tokens per session scan A 74e02d7e7716
rhdh-forge is a skill published in the GitHub repository redhat-developer/rhdh-skills (16 stars, last pushed 2d ago), licensed Apache-2.0. It adds 140 tokens to every session and 1,850 once invoked, about $0.0007 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…