Claude-Mind: Skill for Claude Code

.claude/skills/backlog-report/SKILL.md

backlog-report is a skill for Claude Code from zkysar1/Claude-Mind. It costs 101 tokens per session (4,833 once invoked), scanned A, original, MIT.

A report that turns an agent's aspirations and goals into a sprint-planning backlog, which is a prioritized list of work for a development cycle.

In plain words
What is it for?
Use it to generate or review a markdown backlog containing aspirations, ranked goals, blocked work, and actions requiring the user's attention.
Why use it?
It puts goals, scores, blockers, and actions in one document so the next work can be planned and copied into a project workflow.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is zkysar1/Claude-Mind's own configuration. It tells Claude Code how to work on Claude-Mind itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Claude-Mind configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zkysar1/Claude-Mind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zkysar1/Claude-Mind/main/.claude/skills/backlog-report/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/zkysar1/Claude-Mind

Made for: Claude Code.

Wrote 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.

agentmods badge for backlog-report

README.md
[![agentmods](https://agentmods.dev/badge/skills/zkysar1/claude-mind/backlog-report/github.svg)](https://agentmods.dev/skills/zkysar1/claude-mind/backlog-report)
Your own site
<a href="https://agentmods.dev/skills/zkysar1/claude-mind/backlog-report"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/backlog-report/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.

agentmods 80×15 button for backlog-report

Your own site · 80×15
<a href="https://agentmods.dev/skills/zkysar1/claude-mind/backlog-report"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/backlog-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,833 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00101 $0.04833
Opus 5 $0.00051 $0.02416
Sonnet 5 $0.00020 $0.00967
Haiku 4.5 $0.00010 $0.00483

Measured 8d ago against content hash 4870a196d99d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

backlog-report 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 8d 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.

.claude/skills/backlog-report/SKILL.md · 435 lines

How it starts

The opening of the file, as written. The whole thing — 435 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/backlog-report — Sprint Planning Backlog

Generates a complete, copy-pasteable markdown backlog of all aspirations, goals, scores, blockers, and user action items. Writes agents/<agent>/BACKLOG.md and displays a compact terminal summary.

Hybrid skill: user-invocable AND agent-callable. Valid from ANY state. Safe: read-only with respect to agent state (only writes the output file).

Sub-commands

/backlog-report              — Generate full backlog report

Phase 0: Load Conventions

Step 0: Load ConventionsBash: load-conventions.sh with each name from the conventions: front matter. Read only the paths returned (files not yet in context). If output is empty, all conventions already loaded — proceed to next step.

Phase 1: Gather Data

Run these in parallel where possible:

1. Active aspirations (full detail)
   Bash: aspirations-read.sh --active
   → Parse JSON → store as aspirations[]

2. Scored goal rankings
   Bash: goal-selector.sh select
   → Parse JSON → store as scored_goals[]

3. Blocked goals with diagnostics
   Bash: goal-selector.sh blocked
   → Parse JSON → store as blocked_data

4. Pending questions (user review items)
   Read: agents/<agent>/session/pending-questions.yaml
   → Parse YAML → filter status == "pending" → store as pending_questions[]
   → IF file missing or empty: pending_questions = []

5. Active hypotheses
   Bash: pipeline-read.sh --stage active
   → Parse JSON → store as active_hypotheses[]

6. OHS-delta rollup per aspiration (g-245-03)
   Bash: meta-read.sh improvement-velocity.yaml
   → Parse YAML → for each entry, record {goal_id, ohs_delta_since_previous_ohs_run}
   → Build velocity_map[goal_id] = ohs_delta (float OR 'no_ohs_data')
   → IF field missing from entry: treat as 'no_ohs_data' (pre-schema entries)

Phase 2: Build Indexes

1. SCORE MAP — For each goal in scored_goals[]:
     score_map[goal_id] = {score, breakdown, category, recurring, recurring_urgency}

2. BLOCKED MAP — For each goal in blocked_data.blocked_goals[]:
     blocked_map[goal_id] = {reason_group, block_detail}

3. USER GOALS — Scan all goals across aspirations[]:
     # Two passes: (a) all user-routed goals (for the historical-count note),
     # (b) only actionable goals (pending|deferred|blocked) for the dashboard.
     # Without the status filter, the renderer reports completed historical
     # records as "needing you" — observed pollution: 22 of 24 entries
     # were status=completed (g-115-210 / rb-526). Status filter applies
     # ONLY to the "Goals Needing You" surface in section 3b — completed
     # records remain queryable via aspirations-read.sh for audit.
     ACTIONABLE_STATUSES = {"pending", "in-progress", "deferred", "blocked"}
     all_user_goals = [g for g in <all goals> if "user" in g.participants]
     user_goals = [g for g in all_user_goals if g.status in ACTIONABLE_STATUSES]
     # Counts for the render-time note (used in section 3b):
     total_user_routed = len(all_user_goals)
     historical_user_routed = total_user_routed - len(user_goals)
     # Each user_goals entry includes: goal_id, aspiration_id, aspiration_title,
     # title, priority, score (from score_map), category, status

4. RECURRING HEALTH — Scan all goals across aspirations[]:
     IF goal.recurring == true:
       IF lastAchievedAt is null: overdue_by = infinity (never completed — always most overdue)
       ELSE: overdue_by = max(0, hours_since(lastAchievedAt) - interval_hours)
       Add to recurring_list[]: goal_id, title, interval_hours, lastAchievedAt, overdue_by, currentStreak
     Sort recurring_list by overdue_by descending

5. TESTABLE HYPOTHESES — Filter active_hypotheses[]:
     IF resolves_no_earlier_than is null/missing OR resolves_no_earlier_than <= today:
       add to testable_hypotheses[]
     Sort by confidence descending

6. OHS_DELTA_MAP — For each active aspiration, sum OHS deltas of its completed goals:
     ohs_delta_map[asp_id] = {"sum": float_or_na, "scored": int, "total_completed": int}
     FOR EACH asp in aspirations[]:
       numeric_deltas = []
       completed_count = 0
       FOR EACH goal in asp.goals WHERE status == "completed":
         completed_count += 1
         delta = velocity_map.get(goal.id, 'no_ohs_data')
         IF isinstance(delta, (int, float)):
           numeric_deltas.append(delta)
       IF numeric_deltas:
         ohs_delta_map[asp.id] = {"sum": round(sum(numeric_deltas), 2), "scored": len(numeric_deltas), "total_completed": completed_count}
       ELSE:
         ohs_delta_map[asp.id] = {"sum": "n/a", "scored": 0, "total_completed": completed_count}
     # Display: "+0.45 (3/12)" when scored > 0; "n/a" when no OHS-tracked goals yet

Read the full file on GitHub · 435 lines

Changes

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.

  1. 8d ago First seen · 435 lines · 101 tokens per session scan A 4870a196d99d

Subscribe to this mod's changes

backlog-report is a skill published in the GitHub repository zkysar1/Claude-Mind (5 stars, last pushed today), licensed MIT. It adds 101 tokens to every session and 4,833 once invoked, about $0.0005 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.