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 dwarvesf/dwarves-kit --skill backlog-reconcilegit clone --depth 1 https://github.com/dwarvesf/dwarves-kitWrote 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/dwarvesf/dwarves-kit/backlog-reconcile)<a href="https://agentmods.dev/skills/dwarvesf/dwarves-kit/backlog-reconcile"><img src="https://agentmods.dev/badge/skills/dwarvesf/dwarves-kit/backlog-reconcile/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/dwarvesf/dwarves-kit/backlog-reconcile"><img src="https://agentmods.dev/badge/skills/dwarvesf/dwarves-kit/backlog-reconcile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00100 | $0.03206 |
| Opus 5.5 | $0.00040 | $0.01282 |
| Sonnet 5.5 | $0.00020 | $0.00641 |
| Haiku 4.5 | $0.00010 | $0.00321 |
Grade A, and why
backlog-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 yesterday.
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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backlog reconcile
Scope and triggers
Also fires on "check board rows against their specs", or when a scheduled run asks for the backlog-reconcile audit of a repo. NOT for filing new items onto the board means board-registration tooling, e.g. an adopter's own intake skill. This kit's own docs/reference/FEATURES.md/docs/reference/workflow-paths.md pair is topology-drift's territory, maintainer-only, never this skill's.
Overview
Audit a repo's git-tracked _meta/BACKLOG.md Active queue against reality and ship the fixes
as a PR. This is the backlog-reconcile instance of docs/patterns/audit-loop.md (the pattern
doc's own "Backlog reconcile" SDLC-instances row): every adopter repo gets this schema via
/kit:adopt, so this instance is general-purpose, not maintainer-only like
topology-drift.
The four slots (per the audit-loop pattern)
| Slot | This instance |
|---|---|
| Item set | every row of the target repo's _meta/BACKLOG.md Active queue, enumerated via lib/board/backlog.sh board (id/title/status) plus a raw read of the file for each row's Target artifact cell |
| Contract | a row's Status matches reality: (a) a shipped row not exempted by a _meta/megagoals/ target artifact must have already dropped off the queue; (b) a Target artifact naming SPEC-NNN must point at a real file whose own Status: header agrees with the board's Status; (c) a (tiny, no spec) row's executing/shipped claim must have a git-log match |
| Evidence class | Tier 1: mechanical, batched (file existence, grep -m1 header extraction, one batched git log --grep -F pass). Tier 2: agents/audit-scanner.md, dispatched only on the Tier-1 delta, chunked ~25-30 rows per call, fed any gh evidence this skill gathers itself |
| Apply mechanics | the ONLY mutation is bash lib/board/backlog.sh set <ID> <state> [note] (mechanical, preserves annotation prose); best-effort per row; PR-gated |
Process
- Refusal guard. REFUSE if the target repo has no
lib/board/backlog.shor no_meta/BACKLOG.md(unadopted repo, nothing to reconcile); name what's missing and stop.
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.
- yesterday Changed 1a159090ce64
- 8d ago Changed · +2 lines 9b6a7f3cd0ea
- 1mo ago Changed · +4 lines · -55 tokens per session 86e188471925
- 1mo ago Changed · +22 lines 9921fa11b600
- 1mo ago Changed · +6 lines 7f4d060b190e
- 1mo ago Changed 38d55526324f
- 1mo ago First seen · 147 lines · 155 tokens per session scan A 766f45570001
backlog-reconcile is a skill published in the GitHub repository dwarvesf/dwarves-kit (12 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 3,206 once invoked, about $0.0004 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 2026-09-04.
Other skills, from other repositories
spec-kitty-implement-review
Orchestrate the implement-review loop for Spec Kitty work packages using any configured agent. Covers agent dispatch, state transitions, rejection cycles, arbiter escalation, and dependency-aware sequencing across all 13 supported coding agents. Triggers: "implement and review WPs", "run the implement-review loop"…
spec-kitty-runtime-review
Review runtime-owned outputs using the Spec Kitty review workflow surface, then direct approval or rejection with structured feedback. Triggers: "review this work package", "check runtime output", "approve this step", "review WP", "is this WP ready to approve", "check this implementation". Does NOT handle: setup-only…
project-specification
Transforms project briefs into testable specifications with user stories and acceptance criteria. Use after brainstorming, before planning.
fable-validate-loop
Use when the user asks to validate a GitHub issue with Fable 5.1 and then autonomously drive it to a reviewed PR in one shot — "fable-validate-loop", "fable validate and work on #N", "fully automate issue #N with fable". Runs fable-validate, auto-applies its update-issue edits when the verdict calls for it, has…
triage
Move issues and external PRs through triage roles — categorise, verify, grill if needed, write agent-ready briefs.
triage
Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.