Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add artemnovichkov/skills/plugin install sdlcWrote 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/artemnovichkov/skills/intent)<a href="https://agentmods.dev/commands/artemnovichkov/skills/intent"><img src="https://agentmods.dev/badge/commands/artemnovichkov/skills/intent/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/artemnovichkov/skills/intent"><img src="https://agentmods.dev/badge/commands/artemnovichkov/skills/intent.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 | $0.00027 | $0.00504 |
| Opus 5 | $0.00014 | $0.00252 |
| Sonnet 5 | $0.00005 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
intent 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 yesterday.
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.
What it actually says
Stage 1 — Capture as intent
Turn a rough idea into a committed, machine-readable intent. This is the cheapest stage to be wrong in: the goal is a document worth arguing with, not a finished spec.
$ARGUMENTS is the raw idea. If empty, ask the user what they want to build or fix.
Workflow
1. Interview, do not transcribe
Ask about whatever the idea does not already answer — one round, not an interrogation:
- What is broken or missing today, and who feels it?
- What does "done" look like from outside the code?
- Which parts of the system does this touch? (search the repo and propose an answer instead of asking blind)
- What is explicitly out of scope?
- What constraints are fixed — deadline, platform, dependency, compatibility?
If the repo has CLAUDE.md, read it first so questions do not re-ask what the repo already documents.
2. Draft the artifact
Use ${CLAUDE_PLUGIN_ROOT}/templates/intent.md. Write sdlc/intent/<slug>.md where <slug> is kebab-case, derived from the title, max 5 words. Check for a slug collision in sdlc/intent/ first.
Rules for the draft:
- Problem stated as an observed fact, not as a solution in disguise.
- Outcome measurable by someone who cannot read the diff.
- Open questions listed honestly — an intent with zero open questions is usually a lie, and the list is what the spec stage resolves.
- No implementation detail. If you catch yourself naming a class or a file, it belongs in the spec or plan.
Status: draft.
3. Hand back for correction
Show the draft and ask for corrections. Iterate until the user accepts it, then flip Status: to accepted.
4. Offer the commit
Print the exact command:
git add sdlc/intent/<slug>.md && git commit -m "intent: <title>"
Do not run it without the user saying so. Then tell them the accepted intent unlocks /sdlc:spec <slug>.
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.
- yesterday First seen · 51 lines · 27 tokens per session scan A 198dd292c0da
intent is a command published in the GitHub repository artemnovichkov/skills (36 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 504 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 2026-09-07.
Other commands, from other repositories
collaborative-spec-builder-existing
Build an aspirational specification for existing code and identify gaps to address.
speckit.tasks
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
speckit.taskstoissues
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
tracker-sync
Project a flow spec to a tracker (Linear/GitHub/GitLab/Jira) and reconcile body/status/comments two-way — projection, not coordination. NOT plan-sync (/flow-next:sync).
land
Cadence-tick autonomous PR babysitter (CI-fix, resolve, converge, merge, close, release).
work
Work unit management: list, continue, checkpoint, switch.