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 Parad0x-Labs/openclaw-skills --skill correction-intentgit clone --depth 1 https://github.com/Parad0x-Labs/openclaw-skillsWrote 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/parad0x-labs/openclaw-skills/correction-intent)<a href="https://agentmods.dev/skills/parad0x-labs/openclaw-skills/correction-intent"><img src="https://agentmods.dev/badge/skills/parad0x-labs/openclaw-skills/correction-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/skills/parad0x-labs/openclaw-skills/correction-intent"><img src="https://agentmods.dev/badge/skills/parad0x-labs/openclaw-skills/correction-intent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.00406 |
| Opus 5.5 | $0.00021 | $0.00162 |
| Sonnet 5.5 | $0.00010 | $0.00081 |
| Haiku 4.5 | $0.00005 | $0.00041 |
Grade A, and why
correction-intent-tagger 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 23d 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.
What it actually says
Correction vs Instruction Tagger
Detects when a message corrects a prior one and builds an active state where corrections override originals.
The problem nobody benchmarks: "use Redis" at msg 20, "actually use Postgres" at msg 47. Standard compression keeps both. This tagger supersedes Redis, surfaces only Postgres in activeInstructions.
Usage
from correction_intent import tag_messages, build_active_state, inject_active_state
tagged = tag_messages(messages)
state = build_active_state(tagged)
system_injection = inject_active_state(state)
# inject into system prompt — agent sees CURRENT STATE, not history
What it detects
- CORRECTION: "actually", "scratch that", "instead", "I meant", implicit topic override
- INSTRUCTION: new directive
- ADDITIVE: "also", "additionally" — extends without overriding
- QUERY: question, not actionable
- ACK: "ok", "got it", "understood"
Correction chain receipt
from correction_intent import correction_chain_receipt
receipt = correction_chain_receipt(state, session_id)
# receipt["chain_root"] is the anchorable 32-byte root; a devnet receipt_anchor is
# available at HSdEQWunzPtNqdzv5HfXuA3zwPLpgTXRyfbndnGamhXs; pass it explicitly to an anchoring client
Part of the Parad0x Labs stack: github.com/Parad0x-Labs/openclaw-skills/tree/main/plugins/correction-intent
What ships with it
1 file 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.
- 23d ago Changed · +1 lines e0bd3dc55e7a
- 2mo ago First seen · 46 lines · 52 tokens per session scan A 00a736e26cfc
correction-intent-tagger is a skill published in the GitHub repository Parad0x-Labs/openclaw-skills (23 stars, last pushed 17d ago), licensed MIT. It adds 52 tokens to every session and 406 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 2026-08-30.
Other skills, from other repositories
brain-save
Create and manage governed memories by capturing one fact, decision, pattern, or convention, or by retiring an outdated memory. This is side-effecting and never auto-fires. Use when preserving a durable fact without a full recompile or changing a memory's lifecycle. Trigger with "/brain-save".
brain
Search and analyze governed notes, decisions, runbooks, and conventions, returning a qmd:// citation for every supported claim. Use when checking what the brain has captured about architecture, infrastructure, decisions, or operating practices. Trigger with "/brain", "ask the brain", or "check my knowledge base".
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
ligandmpnn
Inverse-fold a backbone with ligand, nucleic-acid, and metal context using LigandMPNN (Dauparas et al. 2023, github.com/dauparas/LigandMPNN). Reach for this skill to redesign the residues lining a binding pocket around a bound small molecule or cofactor, to design metal-coordinating sites where the geometry must be…
evo2
Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring…
bo-process-optimization
A method for examining a business workflow to find waiting, rework, handoff waste, and other delays, then proposing improvements and ways to measure them. It separates observed facts from possible explanations and suggestions.