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 JairoTorregrosa/jaiskills/plugin install jaiskillsWrote 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/jairotorregrosa/jaiskills/constatar-plan)<a href="https://agentmods.dev/skills/jairotorregrosa/jaiskills/constatar-plan"><img src="https://agentmods.dev/badge/skills/jairotorregrosa/jaiskills/constatar-plan/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/jairotorregrosa/jaiskills/constatar-plan"><img src="https://agentmods.dev/badge/skills/jairotorregrosa/jaiskills/constatar-plan.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 | $0.00049 | $0.00827 |
| Opus 5 | $0.00024 | $0.00413 |
| Sonnet 5 | $0.00010 | $0.00165 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
constatar-plan 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 12d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring constatar plans
A plan.toml declares units of work, their executors, and how each unit is
verified. The parser is strict (deny_unknown_fields, cycles rejected,
references validated, paths resolved against the plan file's directory) —
a plan that parses will not fail on schema surprises mid-run.
Full field-by-field schema: ${CLAUDE_PLUGIN_ROOT}/references/constatar/plan-schema.md.
The 6-rung verification ladder: ${CLAUDE_PLUGIN_ROOT}/references/constatar/ladder.md.
Skeleton
[meta]
name = "my-run"
repo = "." # git repo; REQUIRED for red_first, protected_paths,
# model rungs (4-6), and parallel execution
[[unit]]
name = "write-feature-tests" # no "::" (reserved)
role = "executor"
adapter = "claude" # claude | codex
prompt_file = "prompts/tests.md" # relative to this file
permission = "accept-edits" # accept-edits | unrestricted | read-only
controlled = true # false => surprises tagged [uncontrolled]
[unit.verify]
oracle = ["cargo test --test feature --no-run"] # compile, don't pass/fail
[[unit]]
name = "implement-feature"
adapter = "claude"
prompt_file = "prompts/impl.md"
[unit.verify]
oracle = ["cargo test", "cargo clippy -- -D warnings"]
adversarial = true # rung 4: cross-family skeptic
red_first = true
tests_from = "write-feature-tests" # REQUIRED with red_first (implies depends_on)
red_first_cmds = ["cargo test --test feature"] # the instruments calibrate() reds
protected_paths = ["tests/"] # extends defaults (Cargo.toml, build.rs, ...)
test_list_cmd = "cargo test --lib -- --list"
Rules the parser enforces (fail at parse, never mid-run)
red_first = truerequirestests_fromAND non-emptyred_first_cmds.held_outrequires a non-emptyoracle(the gap needs a visible baseline); held-out commands must never appear in any prompt file.- Model rungs (
adversarial,judge,peer_review) requirerepoand two adapter families configured; thresholds (hacking_gap_threshold,judge_gap_threshold) are finite in [0,1], default 0.3. - Units at the same dependency depth (parallel candidates, repo set) must share ONE adapter family — the other family stays free to arbitrate — and must declare at least one deterministic rung (oracle/property), because merged states are re-verified deterministically after integration.
depends_onforms a DAG; duplicate names, unknown adapters, missing prompt files are parse errors.
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.
- 12d ago First seen · 77 lines · 49 tokens per session scan A 3be24b787ab7
constatar-plan is a skill published in the GitHub repository JairoTorregrosa/jaiskills (5 stars, last pushed 11d ago), licensed MIT. It adds 49 tokens to every session and 827 once invoked, about $0.0002 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
swarmclaw
AI agent runtime and multi-agent orchestration platform. Teaches agents how to use SwarmClaw's 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. Use when an agent is running on SwarmClaw and needs to understand the platform's capabilities.
eliza
Skill "eliza" from aomi-labs/skills, covering elizaos, what you probably got wrong, installation, cli (recommended for new projects) and from source (contributor workflow).
update-harness
Update an existing Claude Code harness — check for outdated components, duplication with official features, missing patterns, and improvement opportunities, then apply approved changes. Use whenever: 'update harness', 'update my harness', 'is my harness up to date', 'harness outdated', 'optimize harness', 'check my…
agent-orchestrator
Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.
create-harness
Generate a complete, project-specific Claude Code harness — agents, skills, hooks, CLAUDE.md rules — tailored to any codebase. Use whenever someone says 'create a harness', 'set up agents for this project', 'configure Claude Code', 'build an agent team', 'make this project AI-ready', 'harness this project', or any…
help
Get oriented with the solopreneur plugin — see your AI team, check project status, and get suggestions for what to do next. Use when you're getting started or need a refresher.