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.
git clone --depth 1 https://github.com/gf-labs/claude-toolboxWrote 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/commands/gf-labs/claude-toolbox/consolidate-tasks)<a href="https://agentmods.dev/commands/gf-labs/claude-toolbox/consolidate-tasks"><img src="https://agentmods.dev/badge/commands/gf-labs/claude-toolbox/consolidate-tasks/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/commands/gf-labs/claude-toolbox/consolidate-tasks"><img src="https://agentmods.dev/badge/commands/gf-labs/claude-toolbox/consolidate-tasks.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 | $0.00000 | $0.01222 |
| Opus 5 | $0.00000 | $0.00611 |
| Sonnet 5 | $0.00000 | $0.00244 |
| Haiku 4.5 | $0.00000 | $0.00122 |
Grade A, and why
consolidate-tasks scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your role
Orchestrate the consolidate-tasks pipeline. Work through the steps below interactively — pause for user confirmation where noted.
Step 0 — Preflight + collect
Verify TaskWarrior is available:
task --version 2>/dev/null || { echo "TASK_MISSING"; exit 1; }
task udas 2>/dev/null | grep -cE "^(size|source)" | grep -q "^2$" || echo "MISSING_UDAS"
- If
TASK_MISSING: stop — "TaskWarrior not found. Install it (brew install task) and addsizeandsourceUDAs to~/.taskrcbefore running this skill." - If
MISSING_UDAS: stop — "Required UDAs (size, source) not found in ~/.taskrc. See the claude-toolbox TaskWarrior design spec."
Run collection:
python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/collect-tasks.py $ARGUMENTS > /tmp/consolidate-manifest.json
echo "EXIT:$?"
If exit code nonzero, read /tmp/consolidate-manifest.json for the error message, print it, and stop.
Read /tmp/consolidate-manifest.json. Sum across all repos and print:
N repos · M tracking files · K code comments · J GitHub issues
Where:
- repos = number of entries in
repos[] - tracking files = count of distinct
source_filevalues wheresource_type == "markdown" - code comments = count of items where
source_type == "code" - GitHub issues = count of items where
source_type == "github"
If all item counts are zero across all repos: print "No items found to migrate." and stop.
Step 1 — Confirm slugs
For each repo in the manifest:
- Print:
[repo-name] → [slug] - If
tw_slugs_present: true, show the sub-slug mappings from the items (group by inferred_slug per source_file) - If
files_with_no_slug_mappingis non-empty, flag each:⚠ [file] — no sub-slug mapping (will default to [slug])
Ask: "Confirm these slugs, or provide overrides:"
Wait for confirmation. If overrides provided, apply them to all matching items in /tmp/consolidate-manifest.json using the Edit tool.
Step 2 — Dedup + judgment
For each unique inferred_slug value in the manifest, run:
task rc.verbose=nothing project:[SLUG] all 2>/dev/null
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.
- 9d ago First seen · 142 lines · 0 tokens per session scan A 63610cd5a31c
consolidate-tasks is a command published in the GitHub repository gf-labs/claude-toolbox (2 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,222 tokens. 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 commands, from other repositories
epic-claim
Claim an epic issue, stamp coordination state, and sync local ownership.
epic-review
Mark epic review requested, approved, or changes requested.
amend-plan
Plan Amend - Discuss and apply amendments to a plan.json implementation plan.
status
The state of play, computed fresh: branch, dirty files, the active sprint, open work, index freshness.
plan-start
5-phase planning command: PRD analysis, design review, technical decisions, dynamic research team, metrics. Produces a complete implementation plan + ADRs before any code is written.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.