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 commands/gf-labs/claude-toolbox/backloggit 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/backlog)<a href="https://agentmods.dev/commands/gf-labs/claude-toolbox/backlog"><img src="https://agentmods.dev/badge/commands/gf-labs/claude-toolbox/backlog.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 | $0.00010 | $0.00634 |
| Opus 5 | $0.00005 | $0.00317 |
| Sonnet 5 | $0.00002 | $0.00127 |
| Haiku 4.5 | $0.00001 | $0.00063 |
Grade A, and why
backlog 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 4d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arguments
$ARGUMENTS
If arguments provided: use them as the item description (with optional tags and size). If no arguments: derive a task from this session's recent context (open threads, incomplete work, things mentioned as "later" or "TODO").
Your role
Add a new task to TaskWarrior for the current project.
Step 1 — Determine project slug:
echo "SLUG: $(python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/_slug.py)"
If not in a git repo: ask the user for the project slug (format: domain.reponame).
Step 2 — Check for existing similar task:
task project:[slug] list
If a closely matching task exists, say so and stop.
Step 3 — Draft task add + annotation:
From $ARGUMENTS, extract:
- Short title (required, ≤ 70 chars): a scannable lede — the verb + object, no qualifiers, no bench specs, no env-var lists, no parentheticals
- Details (when present): everything else from the input — benchmarks to run, env vars to set, rationale, things to skip, gated-on conditions, links. Becomes an annotation
- Type tag (infer from description):
+command,+agent,+hook,+pipeline,+infra,+research - Size (default
size:S):size:XS|S|M|L|XL - Priority (omit unless clearly blocking):
priority:H|M|L - Special status:
wait:somedayfor truly indefinite deferrals;+blockedfor gated items
If the user's input is one short sentence with no rationale, just use it as the title — no annotation needed. Default behavior is to split longer input into title + annotation, not stuff everything into the title.
Draft commands:
task add "[short title]" project:[slug] +[type] size:[S] source:manual
# only if details present:
task annotate [ID] "[details]"
Show the draft to the user. If the split between title and details is ambiguous, confirm before executing.
Step 4 — Execute:
Run task add first, capture the new task ID from output (e.g. Created task 563.), then run task annotate [ID] ... if details were drafted.
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.
- 4d ago First seen · 63 lines · 0 tokens per session scan A d6faeba35977
backlog is a command published in the GitHub repository gf-labs/claude-toolbox (2 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 634 once invoked, about $0.0001 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 commands, from other repositories
feature
Ciclo completo de desarrollo: producto, arquitectura, desarrollo, QA, docs, entrega.
sync-github
Ejecuta SonIA Sync: refleja el tablero local en GitHub Issues usando gh CLI.
status
The state of play, computed fresh: branch, dirty files, the active sprint, open work, index freshness.
v-orchestrate
Materialize a Compound V execution manifest from a plan (or an accepted fast-path pre-eval). Applies the routing policy and writes manifest.yaml plus an initial state.json into docs/superpowers/execution/ / — without dispatching. Binds every pre-eval-backed run. Use this to inspect or edit the manifest before…
whats-next
Show current project status and suggest next steps.
specmanager-build
Build one phase of a SpecManager feature's plan via the builder subagent. Stops at the phase boundary; never advances.