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/maximumsoft-co-ltd/claude-flightdeck/backlog-migratenpx skills add Maximumsoft-Co-LTD/claude-flightdeck --skill backlog-migrategit clone --depth 1 https://github.com/Maximumsoft-Co-LTD/claude-flightdeckWrote 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/maximumsoft-co-ltd/claude-flightdeck/backlog-migrate)<a href="https://agentmods.dev/skills/maximumsoft-co-ltd/claude-flightdeck/backlog-migrate"><img src="https://agentmods.dev/badge/skills/maximumsoft-co-ltd/claude-flightdeck/backlog-migrate.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 | $0.00134 | $0.02103 |
| Opus 5 | $0.00067 | $0.01052 |
| Sonnet 5 | $0.00027 | $0.00421 |
| Haiku 4.5 | $0.00013 | $0.00210 |
Grade A, and why
backlog-migrate 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 5d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/backlog-migrate — one-time reconcile of a drifted backlog
Announce: Using /backlog-migrate to reconcile the backlog against real sprint evidence and split hot/cold.
The disease this cures: a backlog.md whose Status column drifted from reality
(rows marked verified/scheduled/blob-text that were actually shipped sprints
ago), grown to hundreds of KB because done items never left the file, with a
sprints/ dir cluttered by dozens of closed folders. The result is /work
re-picking already-shipped work. This skill rebuilds trust from evidence, not
from the status column — once. After it, the mechanism (scripts/backlog.sh
check/sweep/verify + the CI gate) keeps it clean.
Token budget
- Never Read the giant
backlog.mdwholesale into the main session. Dispatch the per-row evidence gathering to anExploresubagent (read-heavy fan-out oversprints/) — it returns a slim classification table, not file dumps. - The main session holds only: the classification table + the rewrite it authors.
- Use
scripts/backlog.shfor the deterministic steps (sweep/index/check/ archive-sprints) — 0 LLM tokens.
Preconditions
- Clean git tree on a fresh branch (
chore/backlog-migrate). Everything this skill does is a reviewable diff; the originalbacklog.mdis preserved in git — nothing is deleted, only moved/rewritten. Confirm with the user first. - The new schema docs are in place (
docs/designs/_templates/BACKLOG_ENTRY_TEMPLATE.mdStatus enum:open | wip S## | done S## | wontfix | superseded-by B###).
Procedure
Legacy structures you'll actually meet (real-world)
A drifted backlog is NOT one clean ## Active table. Expect, in one file:
- Multiple status-bearing sections (
## Active,## Unscheduled,## Scheduled,## Deferred,## Archive) with inconsistent columns — some end inStatus, some inSource, some in aTasknumber with no status at all. - Initiative sub-tables (
## ... Initiative (INIT-001)→### Phase F/T/W/…), each its own table — a common place closed work hides (the## Activesweep never reached it). - Detail blocks (
### B### — …) holding prose state below the tables. - Blob Status cells: a single cell that is a log —
discovery D067 (ready S130) … **IMPL DONE S130** … promoted dev→main. The real state is buried mid-cell after a stale prefix; a prefix/cutread lies. - A partially-migrated file: the cold archive may already hold a bulk sweep — don't re-process IDs already there.
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.
- 5d ago First seen · 140 lines · 134 tokens per session scan A d8504e734d6a
backlog-migrate is a skill published in the GitHub repository Maximumsoft-Co-LTD/claude-flightdeck (2 stars, last pushed 3mo ago), licensed MIT. It adds 134 tokens to every session and 2,103 once invoked, about $0.0007 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
vc-generate-phase-program
Generate kickoff artifacts for a multi-phase program: umbrella plan, Program Goal Charter, session-goal block, per-phase plan stubs, and the 7-step per-phase inner loop reference.
vc-intent-clarify
Clarify intent before RIPER-5 phase delegation. Scores ambiguity (4 signals); generates structured multi-choice questions for Tier 2. Two-mode: SIMPLE and DEEP.
vc-agent-strategy-compare
Evaluate 4 execution strategies (sequential, parallel-subagents, workflow, agent-team) for a phase or fan-out task. Outputs 7-signal score table, agent count math, cost guards, and strategy recommendation.
vc-autoresearch
Loop: find gaps → fix → repeat until agents find no gaps or a metric goal is hit. Shared loop primitive for PVL, EVL, and standalone quality runs.
vc-generate-closeout
Generate the post-EXECUTE closeout packet for a plan or phase. Includes archive-readiness classification, drift signal scoring, commit checkpoint recommendation, and move-on next-state recommendation.
vc-validate-findings
Use when running VALIDATE V2-V3 fan-out. Two-layer investigation (4 dimension agents + per-section feasibility agents) synthesized into PASS/CONDITIONAL/BLOCKED net gate. Strategy-agnostic.