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 forger-labs-hq/researchforge --skill researchforge-shipgit clone --depth 1 https://github.com/forger-labs-hq/researchforgeWrote 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/forger-labs-hq/researchforge/researchforge-ship)<a href="https://agentmods.dev/skills/forger-labs-hq/researchforge/researchforge-ship"><img src="https://agentmods.dev/badge/skills/forger-labs-hq/researchforge/researchforge-ship/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/forger-labs-hq/researchforge/researchforge-ship"><img src="https://agentmods.dev/badge/skills/forger-labs-hq/researchforge/researchforge-ship.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 | $0.00045 | $0.00759 |
| Opus 5 | $0.00023 | $0.00380 |
| Sonnet 5 | $0.00009 | $0.00152 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
researchforge-ship 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 10d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship a validated result
Three steps, each more outward-facing than the last. Every one is gated by the engine (contract flags + typed confirmations) and each gate exists for the user to open, not you.
1. Local branch (never pushed)
researchforge ship branch --json
Requires shipping.allow_branch_creation in the approved contract and a
typed confirmation — ask the user to run it, or use --yes only with their
explicit go-ahead in this conversation. The engine re-runs the full
benchmark once (pre-ship confirmation) and refuses to ship on failure,
constraint violation, or unconfirmed improvement. The result is one clean
commit on the frozen baseline, as a local branch only — the user's
checkout and remotes are untouched. Report the branch name, commit, and
pre-ship metric from the JSON.
2. Engineering report
researchforge report build --json
Writes .researchforge/reports/engineering-report.md — the full evidence
chain (objective → baseline → experiments → rejected approaches →
validation → recommendation → exact reproduction steps), built from recorded
data only. Offer to walk the user through it.
3. Draft PR (opt-in, pushes to the remote)
researchforge ship pr --json
This pushes one branch to the user's remote and opens a draft PR via
gh. It is double opt-in: shipping.allow_draft_pr must be true in the
approved contract AND a typed push confirmation is required. Confirm with
the user in chat before this step every time; never use --yes here unless
they just told you to push. If the contract flag is off, tell the user how
to enable it (edit researchforge.yaml, re-approve the contract) — do not
look for another way to push.
Open-source / third-party repositories — ask first. Before shipping a PR, ask the user how they relate to the repository:
- They have push access (their own repo, or a repo they maintain):
ship prpushes a feature branch to it and opens the draft PR there. - They do not have push access (an open-source repo they cloned): the
engine detects this, offers to fork into their GitHub account (typed
forkconfirmation — the user must type it), pushes the branch to the fork, and opens a cross-repo draft PR against the upstream. Never fork without that typed consent, and confirm which GitHub accountghis authenticated as (gh api user -q .login) so the fork lands where the user expects.
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.
- 10d ago First seen · 76 lines · 45 tokens per session scan A 8b9216c2ce3e
researchforge-ship is a skill published in the GitHub repository forger-labs-hq/researchforge (8 stars, last pushed 7d ago), licensed Apache-2.0. It adds 45 tokens to every session and 759 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
cloudflare-workers-ci-cd
Complete CI/CD guide for Cloudflare Workers using GitHub Actions and GitLab CI. Use for automated testing, deployment pipelines, preview environments, secrets management, or encountering deployment failures, workflow errors, environment configuration issues.
claude-code-bash-patterns
Claude Code Bash tool patterns with hooks, automation, git workflows. Use for PreToolUse hooks, command chaining, CLI orchestration, custom commands, or encountering bash permissions, command failures, security guards, hook configurations.
definition-of-done
The ordered finish-line runner for any change in this repo — generators, then the asset-integrity refresh last on its own, then the full gate suite, then commit and push; use before declaring any change finished or whenever the stop hook reports uncommitted or untracked changes.
pr-babysit
The repeatable loop for watching a pull request until it is merged or closed, pairing webhook subscription with a scheduled self check-in so CI results, new pushes, and merge-conflict transitions are never missed; use when asked to watch, babysit, or autofix a PR, or right after creating one.
symlink-manager
Create, audit, repair, and document cross-platform symlinks that work correctly on both Windows and macOS/Linux. Use this skill whenever the user mentions symlinks, symbolic links, junction points, .gitconfig symlinks, broken links after git pull, cross-platform path issues, or needs help with ln -s equivalents on…
aws-ci-cd-release-engineer
Review AWS CI/CD and release safety across CodePipeline, CodeBuild, CodeDeploy, GitHub Actions, GitLab, artifact provenance, deployment gates, approvals, tests, progressive delivery, rollback, change correlation, and incident-prevention recommendations. Use when AWS releases or pipelines can affect production…