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/instructa/planr/planr-task-graphnpx skills add instructa/planr --skill planr-task-graphgit clone --depth 1 https://github.com/instructa/planrWhat 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 | $0.00029 | $0.00947 |
| Opus 5 | $0.00015 | $0.00474 |
| Sonnet 5 | $0.00006 | $0.00189 |
| Haiku 4.5 | $0.00003 | $0.00095 |
Grade A, and why
planr-task-graph 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 2d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planr Task Graph
Read and apply the canonical Evidence ownership guard before product graph preparation or making.
Use Planr as the canonical local coordinator. Markdown plans own scope and narrative; the map is the source of truth for live items, links, picks, approvals, logs, reviews, and closure.
Evaluation subcommands run only when the user explicitly requests them, the selected item's acceptance criteria require them, or the maintainer release workflow invokes them. Never invoke them as routine or opportunistic goal, loop, or task-graph work.
Inspect And Work
Before changes:
planr project show --json
planr map show --json
planr map lane --critical
planr map pressure
If missing, initialize the project and run planr doctor --client all.
Work one item at a time:
planr pick --json
planr done <item-id> --summary "<outcome and decisive result>" \
--files <path> --cmd "<build or live command>" \
--tests "<test command>"
Continue only from the typed packet you were authorized to perform. Makers consume work_packet.kind: "outcome"; mode: "finding_repair" repairs named findings on the same ReviewGate without a fix item, and kind: "hold" stops. Read lifecycle state only from work_packet.execution_state.
Require planr.execution_state.v2. Its budget projection is opaque; skills must not recompute budget policy or replace supplied consumed, reserved, protected, available, provenance, digest, or deadline values.
Every closure must be evidence-backed: changed files through --files, commands through --cmd, tests through --tests, remaining risk through context or findings, and a planr review outcome only when an explicit material ReviewGate exists. Plain planr done is the standard outcome settlement. Branch on the returned work_packet.transition and work_packet.kind: continue only for another compatible outcome; stop for a ReviewGate, verification packet, hold, incompatible ownership or scope, or an empty pick. Use --escalate <reason> only for an allowed intentional override, always with --escalation-ref <stable-reference> and --escalation-explanation <why-the-override-is-required>; never use escalation to replace computed materiality. Keep longer work current with planr pick progress, pause, and resume.
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.
- 2d ago First seen · 68 lines · 29 tokens per session scan A 69617e7e4be9
planr-task-graph is a skill published in the GitHub repository instructa/planr (71 stars, last pushed 5d ago), licensed MIT. It adds 29 tokens to every session and 947 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 2026-08-30.
Other skills, from other repositories
auth-web-cloudbase
CloudBase Web Authentication Quick Guide for frontend integration after auth-tool has already been checked. Provides concise and practical Web authentication solutions with multiple login methods and complete user management.
fix-codesign-error
Slash command that inspects a macOS signing or entitlement failure and explains the minimum fix path. Invoke explicitly with /fix-codesign-error — this skill never self-triggers.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
loop-engineering
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).
telnyx-messaging-hosted-curl
Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.