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 skills add ijust/intent-planner --skill intent-improvegit clone --depth 1 https://github.com/ijust/intent-plannerWrote 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/ijust/intent-planner/intent-improve)<a href="https://agentmods.dev/skills/ijust/intent-planner/intent-improve"><img src="https://agentmods.dev/badge/skills/ijust/intent-planner/intent-improve/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/skills/ijust/intent-planner/intent-improve"><img src="https://agentmods.dev/badge/skills/ijust/intent-planner/intent-improve.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 | $0.00057 | $0.02908 |
| Opus 5.5 | $0.00023 | $0.01163 |
| Sonnet 5.5 | $0.00011 | $0.00582 |
| Haiku 4.5 | $0.00006 | $0.00291 |
Grade A, and why
intent-improve 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 2mo 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
intent-improve Skill
Core Mission
- Success Criteria:
- The
.intent/deliverables and the implementation reality (codebase, tests, and progress in the selected specification tool) are evaluated on the three axes (completeness / correctness / coherence) - The evaluation results are presented in the 5 classifications (aligned / intent reinforcement recommended / corrective packet recommended / Decision Rules update recommended / invariant violation detected), with evidence (file / relevant text)
- Only the corrections the user approved are reflected into
.intent/(the approval unit is per proposal) - When an unrecorded write-back learning is detected, the skill does not write a delta itself but prompts the user to run
/intent-writeback - On a run whose 5 classifications include
Decision Rules update recommendedorinvariant violation detected, following the provisions ofrules/improve-axes.md, it also prompts the user to run/intent-validate(the check for conformance catch-up) (on a run that does not include them, it does not prompt; it only guides and does not itself make a conformance judgment) - When drift-watch is on, the coherence detections are recorded into drift-log as stage:improve / outcome:missed and a pattern×outcome improvement report is presented (when off / missing / invalid / missing section / missing mode.md, nothing is done; the 5 classifications are unchanged)
- No application code has been changed at all
- The
Execution Steps
Step 1: Collect the current state
- Read the
.intent/deliverables (intent-tree.md / intent-compass.md /.intent/packets/index.md+ the packet files under active/ (cross-cutting read for the completeness axis; do not read archive/) / the per-packet drafts under the selected exit (cc-sdd//openspec//speckit/) / deltas.md). If.intent/is absent, guide the user through setup (installing intent-planner and running/intent-discover) and stop. - Read the mode state in order: the inherited issue directory's
discovery/<slug>-<rand>/mode.md(A34; inherit the issue name that discover output) → else the single.intent/mode.local.md(legacy) → else old.intent/mode.md(the CONTRACT.md read fallback contract). If both are absent, continue with the standard default and announce it. - Collect the implementation reality: the codebase (read-only via Read/Glob/Grep), the presence and placement of tests, the progress of
.kiro/specs/(only if it exists), and the promoted / pending entries of deltas.md. - If the selected specification tool's deliverables are absent, continue without that context. If deltas.md is absent, continue treating it as "no delta records" (non-blocking).
- If a target scope is specified by argument, narrow down to it; otherwise target the whole of
.intent/. - You may partially load compass by domain scope (opt-in; federated-governance / INV101): when the target domain is determined by the domain argument or the case context, read and apply
rules/domain-scope.md. Do not full-load compass; pull only "the case's domain tag +always" with grep + inline tags (extending the INV47 pull discipline into the maintenance loop). The coherence axis's safety net (the cross-cutting matching of drift not tied to a packet, decayed rules, and broken premises) targets all symbols, not narrowed by domain scope (do not weaken detection; B-fed5). For a legacy scaffold with no determinable domain and no tags, fall back to the legacy full read (backward-compatible; O3). Do not change the three-axis evaluation or the five-way classification logic (only the range of loaded symbols changes).
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 84 lines · 57 tokens per session scan A 980e37e11946
intent-improve is a skill published in the GitHub repository ijust/intent-planner (5 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 2,908 once invoked, about $0.0002 per session on Opus 5.5. 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
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
requirements-writer
Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.
orchestration-team
Use when coordinating assignments, selected review boundaries, or blocked work across a rig.
oversight-team
Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention…