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/attebury/remogram/remogram-corenpx skills add attebury/remogram --skill remogram-coregit clone --depth 1 https://github.com/attebury/remogramWhat 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 | $0.00042 | $0.00788 |
| Opus 5 | $0.00021 | $0.00394 |
| Sonnet 5 | $0.00008 | $0.00158 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
remogram-core 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 2d 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.
Remogram Core
Use for Remogram product code (packages/remogram-*, packages/provider-*, tests/**).
Load remogram-consumer when the task is forge/read workflow in another repository with .remogram.json, or when validating Remogram against a consumer checkout.
First commands
remogram provider capabilities --json
remogram doctor --json
remogram repo status --json
npm test
Consumer-repo PR/merge planning (from a configured checkout):
remogram pr view --number <n> --json
remogram pr checks --number <n> --json
remogram merge plan --number <n> --json
Command depth, packet types, and write-policy notes: references/command-cheatsheet.md. Write commands and idempotency: references/write-commands.md.
Product boundary
Remogram emits provider-attributed JSON facts with SHA fields where applicable:
- Git-resolved SHAs —
refs compareandsync planresolve refs via local git. - Forge-reported PR SHAs — PR-by-number commands include forge head/base SHAs; divergent head →
stale_headafter local reconciliation.
Never add workflow or planning-tool metadata to Remogram output — no goal-branch, lane-role, or task-id fields from external planners.
Every successful packet includes: type, schema_version, provider_id, remote_name, repo_id, observed_at, ok.
v1 scope: write_commands lists consumer write ids — CLI/MCP only. Effective policy merges repo config with optional operator overlay after forge-identity bind. Not listed → write_not_configured. Verify live behavior with remogram contract export --json — do not fork field lists in skills.
Keep Remogram packages free of imports from external planning or workflow tooling.
Semantic diff fact layer
Remogram exposes forge/git/ref inventory and change-request fact slices. External planning tools interpret intent, queue selectability, and proof routing — never emitted in remogram JSON.
What ships with it
4 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.
- 2d ago First seen · 76 lines · 42 tokens per session scan A b742386bddd2
remogram-core is a skill published in the GitHub repository attebury/remogram (0 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 788 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
minecraft-modpack-server
Host modded Minecraft servers (CurseForge, Modrinth).
jwt-attack
Decode, forge, brute JWTs when Bearer auth header is seen.
opanel-extension-dev
指导 OPanel 扩展的创建、实现、审查、调试与兼容性迁移。Use when a task mentions OPanel extension development, extension.json, @Extension lifecycle methods, OPanelAPI, extension backend routes, extension sidebar page registration, extension resources/web frontend pages, or OPanel extension event listeners.
compare-version-modules
Compare two server-platform adaptation modules of the same platform but different Minecraft/game versions (e.g. forge-1.21.5 vs forge-1.21.8), surfacing only the real API / 写法 differences by normalizing away package-name and version-string noise. Use when the user asks to 对比/比较/diff two version modules, find what…
forge-workflow
Helps an organization admin manage custom Forge workflows conversationally — both AUTHORING new workflows and DELETING existing org- or team-scoped overrides. Invoke this skill whenever the user asks to "create a workflow", "customize my SDLC", "build a new workflow", "set up a custom process", "author a workflow"…
forge-autopilot
Routes any product, engineering, or software development lifecycle (SDLC/PDLC) activity to Forge. Invoke this skill whenever the user describes work that involves the product development process — across any phase: discovery, definition, planning, execution, review, handoff, release, or reporting. This includes…