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/chrisgagne/grounded-forge/creating-tasksnpx skills add chrisgagne/grounded-forge --skill creating-tasksgit clone --depth 1 https://github.com/chrisgagne/grounded-forgeWrote 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/chrisgagne/grounded-forge/creating-tasks)<a href="https://agentmods.dev/skills/chrisgagne/grounded-forge/creating-tasks"><img src="https://agentmods.dev/badge/skills/chrisgagne/grounded-forge/creating-tasks.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 | $0.00077 | $0.06681 |
| Opus 5 | $0.00039 | $0.03341 |
| Sonnet 5 | $0.00015 | $0.01336 |
| Haiku 4.5 | $0.00008 | $0.00668 |
Grade A, and why
creating-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 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 — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating Tasks
A task axis is the projection direction the corpus is shaped against. References are the row dimension; tasks are the column dimension. The matrix's value is that source material gets pre-projected onto task vocabulary at ingestion time, not re-derived at runtime.
Discipline enforced: verb-and-noun job-naming under Christensen 2016 Jobs-to-be-Done framing. Decision-making is a task (verb-and-noun job in a circumstance). Software-business is a domain (semantic field). A task axis must survive the verb-and-noun rule.
Dialogue skill, one task per session, no subagents. Output feeds creating-applications for assembly.
How this skill is invoked
Normally a sub-skill of creating-applications, not a user-facing entry point. When a user asks to create an application:
- User invokes
creating-applications. creating-applications's task-spec pre-flight checks whether a task spec exists.- If no spec exists,
creating-applicationsinvokes this skill inline: the 9-phase dialogue runs in the user's conversation. - When this skill completes (Phase 8 GO/YELLOW), control returns to
creating-applicationsfor the assembly work.
Standalone invocation is rare: usually when the corpus is being expanded ahead of any specific application.
When to invoke standalone (rare)
- Scoping a task axis without immediately assembling its application.
- An existing domain label is being treated as a task axis but has no verb attached; sharpen the scoping before committing.
- Two candidate axes that look like one (or vice versa); the boundary needs to be spelled.
When not to use
- User asking to create an application: invoke
creating-applicationsinstead. - Task axis already well-scoped and stable: use
creating-applications. - Adding a new source: that's
ingesting-resourcesorcreating-distillations. - Adding a new lens: that's
creating-lenses. Lenses are per-distillation modifiers, not axes.
Inputs
- Optional: a candidate task name or rough idea ("we should have a
risk-assessmentaxis", "I want anincident-reviewaxis"). - Optional: a corpus name (defaults to the active corpus from the
creating-corpussession or working-directory inference). - Optional: existing task axes or sibling axes the new task might overlap with.
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 · 398 lines · 0 tokens per session scan A 47330c10bf13
creating-tasks is a skill published in the GitHub repository chrisgagne/grounded-forge (7 stars, last pushed 15d ago), licensed MIT. It adds 77 tokens to every session and 6,681 once invoked, about $0.0004 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
warpp-workflow-authoring
Author WARPP workflows for Manifold as typed-port dataflow JSON. Use when a user asks to build, create, design, generate, or edit a Flow / workflow / automation / pipeline / DAG in Manifold, or mentions WARPP, workflow nodes, or the /flow builder. Covers the document format, port types and coercions, the builtin node…
manifold-api
Use when an agent needs to inspect or call the local Manifold HTTP API. Provides guidelines and scripts to filter specs before reading and handle payloads safely.
duckduckgo-search
Free keyless web, news, and image search via ddgs.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.