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 firatcand/forge --skill amend-roadmapgit clone --depth 1 https://github.com/firatcand/forgeWrote 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/firatcand/forge/amend-roadmap)<a href="https://agentmods.dev/skills/firatcand/forge/amend-roadmap"><img src="https://agentmods.dev/badge/skills/firatcand/forge/amend-roadmap/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/firatcand/forge/amend-roadmap"><img src="https://agentmods.dev/badge/skills/firatcand/forge/amend-roadmap.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 | $0.00047 | $0.01439 |
| Opus 5.5 | $0.00019 | $0.00576 |
| Sonnet 5.5 | $0.00009 | $0.00288 |
| Haiku 4.5 | $0.00005 | $0.00144 |
Grade A, and why
amend-roadmap 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/amend-roadmap
Mid-flight roadmap mutation. The user has a new task ("we need a caching layer task, depends on T05") and wants it in the roadmap WITHOUT hand-editing phases.yaml or the tracker.
Skill ↔ verb split: this skill collects the fields, previews the plan, and confirms. ALL state mutation goes through forge orchestrate amend-roadmap, which is tracker-first: it creates the tracker issue, wires blocked-by relations, then materializes the task into plans/phases.yaml through the reconcile --pull machinery (staged addition) — phases.yaml stays single-writer. Every step is journaled and resumable.
Preconditions
plans/phases.yamlexists, validates, and has asource:stanza (tracker-bound). If there is nosource:stanza, stop: run/push-to-tracker(greenfield) or/reconcile --pullfirst..forge/settings.yamlhas a workingtracker:block.
Step 1 — Collect fields
Prompt the user for (one round, AskUserQuestion where it helps):
| Field | Constraint |
|---|---|
phase |
existing phase-N[.M] id — show the active phases to pick from |
title |
verb + noun, ≤ 8 words |
description |
1 paragraph |
type |
foundation · data · backend · integration · content · infra · skill · docs |
priority |
P0 · P1 · P2 |
estimate |
S · M · L — XL is refused by the verb ("No XL tasks ship — split them") |
owner_type |
backend-dev · frontend-dev · db-architect · devops-engineer · qa-engineer · security-auditor · design-engineer · integration · human (manual bootstrap work — never auto-dispatched) |
acceptance |
≥ 1 concrete, testable criteria |
depends_on |
task ids (P2-T03) or tracker identifiers (FORGE-93); every dep must already exist AND be tracker-backed |
write_globs |
optional — file globs for overlap classification |
Step 2 — Preview + confirm
Show the user the assembled payload plus what will happen:
New task in phase-2.5 (next id will be computed by the verb, e.g. P2.5-T14):
title: Add caching layer for tracker reads
type/prio: backend · P1 · M · backend-dev
depends_on: P2.5-T03 (FORGE-95)
Plan: 1 tracker issue + 1 blocked-by relation → phases.yaml via reconcile pull.
Proceed? [y/n]
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 · 123 lines · 47 tokens per session scan A 07b0372d1a74
amend-roadmap is a skill published in the GitHub repository firatcand/forge (13 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 1,439 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
github-triage
Triage GitHub issues through a configurable label-based state machine. Use when user wants to triage incoming issues, prepare issues for an autonomous agent, or move an issue between workflow states. Repo inferred from git remote; all GitHub calls go through gh.
to-issues
Decompose a plan, PRD, or spec into independently-grabbable vertical-slice issues (markdown file by default, GitHub issues via flag). Trigger when the user wants implementation tickets, work decomposition, or to convert an implementation plan into parallelizable work. Takes a plan file and emits atomic vertical slices.
loop-build
(loop-engineering) Implements exactly one feature from the BACKLOG.md Backlog — syncs main, acquires the loop lock, creates a feature branch, implements all acceptance criteria with tests, visually inspects UI changes, passes the independent verifier, and opens a PR. Use for Build-mode loop runs, or when asked to…
loop-report
(loop-engineering) Runs the daily Report-mode triage — checks open PRs, CI status and the BACKLOG.md backlog, then updates STATE.md and appends to the run log without writing any code. Use for scheduled daily loop runs, project health checks, or when asked to "triage", "run report mode", or "update the loop state".
to-issues
Decompose a plan, PRD, or spec into independently-grabbable vertical-slice issues (markdown file by default, GitHub issues via flag). Trigger when the user wants implementation tickets, work decomposition, or to convert an implementation plan into parallelizable work. Takes a plan file and emits atomic vertical slices.
github-triage
Triage GitHub issues through a configurable label-based state machine. Use when user wants to triage incoming issues, prepare issues for an autonomous agent, or move an issue between workflow states. Repo inferred from git remote; all GitHub calls go through gh.