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/firatcand/forge/reconcilenpx skills add firatcand/forge --skill reconcilegit 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/reconcile)<a href="https://agentmods.dev/skills/firatcand/forge/reconcile"><img src="https://agentmods.dev/badge/skills/firatcand/forge/reconcile.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 | $0.00037 | $0.01775 |
| Opus 5 | $0.00018 | $0.00888 |
| Sonnet 5 | $0.00007 | $0.00355 |
| Haiku 4.5 | $0.00004 | $0.00178 |
Grade A, and why
reconcile 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/reconcile
Bidirectional sync between plans/phases.yaml (local) and the configured tracker (Linear / GitHub / Notion).
--pull: tracker → phases.yaml. Updates titles anddepends_onfor matched tasks. Reports orphans (in yaml but not in tracker), new tracker issues, and unmanaged issues (created outside forge).--push: phases.yaml → tracker. Renders each task's body fromdescription+acceptanceand callsTracker.updateIssueBody. Best-effort: per-task errors don't abort the loop.--dry-runis supported on both directions — preview without writing.
Per spec/ORCHESTRATOR.md §CLI surface: this is the canonical bidirectional sync. No conflict-resolution UI — when the same task is edited in both places, the tracker (for --pull) or the local yaml (for --push) wins. Resolve via git diff and re-run.
Preconditions
plans/phases.yamlexists and validates againstPhasesSchema.forge/settings.yamlexists with atracker:block (validated byTrackerConfigSchema)- The tracker is reachable (Linear API key in env /
gh auth statusok /ntnCLI installed + authed)
Step 0 — Direction
Ask the user (or accept arg): --pull or --push?
- Use
--pullwhen: tracker has changes you want to mirror locally (someone closed an issue, retitled it, edited the blocker graph). - Use
--pushwhen: you've editedplans/phases.yamllocally (refined a description, fixed acceptance criteria) and want tracker bodies to match.
Step 1 — Dry-run preview
forge orchestrate reconcile --pull --dry-run --json
# or
forge orchestrate reconcile --push --dry-run --json
Parse the JSON output:
{ "ok": true, "data": {
"direction": "pull",
"dry_run": true,
"pull": {
"updated": [{ "task_id": "...", "tracker_issue_id": "...", "changes": [...] }],
"removed": [{ "task_id": "...", "tracker_issue_id": "..." }],
"added": [{ "tracker_issue_id": "...", "identifier": "...", "title": "...", "forge_task_id": "..." }],
"unmanaged": [{ "tracker_issue_id": "...", "identifier": "...", "title": "..." }]
},
"applied": false
}}
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 · 160 lines · 37 tokens per session scan A d41611eb2b6a
reconcile is a skill published in the GitHub repository firatcand/forge (13 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 1,775 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 2026-08-30.
Other skills, from other repositories
ospec-change
Create or advance a lightweight OSpec change using the classic fast workflow.
prospec-knowledge-generate
Generate AI Knowledge - Read raw-scan.md, analyze project structure, autonomously decide module boundaries, and produce Recipe-First module READMEs and index. Triggers: generate knowledge, analyze project, module split, 產生知識, 知識庫, 分析專案, 模組拆分.
submit-pr
Open a prospec pull request in the house format — push the change's two commits, write the Traditional Chinese body, and link it to its issue. Triggers: submit pr, open pr, 開 PR, 送 PR, 發 PR, pull request, 提交 PR.
prospec-explore
Explore - Requirement exploration, problem investigation, and solution comparison partner. Triggers: explore, compare, investigate, unsure, clarify, 探索, 比較, 釐清, 調查, 不確定.
prospec-knowledge-update
Incremental Knowledge Update - Parse delta-spec.md to identify affected modules, scan source code, and update module README, index.md, and module-map.yaml incrementally. Triggers: knowledge update, incremental update, sync knowledge, update docs, 更新知識, 增量更新, 同步知識, 更新文件.
prospec-plan
Plan Implementation - Convert User Story into technical implementation plan (plan.md) and change specification (delta-spec.md). Triggers: plan, architecture, technical plan, 規劃, 架構規劃, 技術規劃.