Borrowing it
Nothing to install: this file belongs to stellar-experimental/stellar-raven. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/stellar-experimental/stellar-raven/main/.agents/skills/truth-maintenance/SKILL.mdgit clone --depth 1 https://github.com/stellar-experimental/stellar-ravenWrote 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/stellar-experimental/stellar-raven/truth-maintenance)<a href="https://agentmods.dev/skills/stellar-experimental/stellar-raven/truth-maintenance"><img src="https://agentmods.dev/badge/skills/stellar-experimental/stellar-raven/truth-maintenance.svg" alt="Measured on agentmods" 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 | $0.00088 | $0.02006 |
| Opus 5 | $0.00044 | $0.01003 |
| Sonnet 5 | $0.00018 | $0.00401 |
| Haiku 4.5 | $0.00009 | $0.00201 |
Grade A, and why
truth-maintenance 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 7d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Truth maintenance
This is the coordinator skill. It does not replace the lane runbooks:
live-drift-resolutionowns catalog/inventory/spec/op-class drift from live upstream services.run-evalsowns eval instrument selection, result review, and eval-round closeout.golden-truthowns any golden question/answer/key-fact/avoid/source/grader-note change.improvements-pipelineownsimprovements/, intake, probes, upstream issue/PR tracking, and index/lint.
Use this skill when the work crosses lanes or when the user asks for "truth is up to date" rather than a single drift issue. The product is a maintenance round recorded in a ledger, with lane verdicts, evidence, follow-ups, and cleaned-up spawned work.
Orchestration contract
Use the global herdr skill for spawning, monitoring, and cleanup: one pane per lane, split from
your own pane. Select model and effort explicitly per AGENTS.md. This skill adds only
truth-maintenance lane structure.
Open one ledger for the round at .agents/rounds/<YYYY-MM-DD>-truth-maintenance.md.
Use fixed headings so spawned agents can append without clobbering each other:
# Truth maintenance <YYYY-MM-DD>
## Scope
## Lane plan
## Drift verdict
## Eval verdict
## Golden verdict
## Improvements/issues/PR verdict
## Own-repo todos
## Decisions
## Final checklist
By default, workers research/review and append to ledger; coordinator owns repo edits. Delegate patches only when write set is narrow, explicit, and disjoint.
Reviewer and author are separate roles. A spawned reviewer must re-derive from files, diffs, live probes, or GitHub state, not rubber-stamp the coordinator's summary. Let reviewers finish unless the user cancels or they clearly error.
Stale-gospel queue (the freshness lane — owned by this skill)
Golden freshness is not maintained by batch re-audits; it is a standing due-date queue.
Every scheduled-freshness QA case carries a truth.reverifyBy date, and
npm run eval:qa:lint -- --stale fails on any past-due case — wired into PR CI and the daily
refresh workflow, so a date passing fires within 24 hours. This skill owns that queue:
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.
- 7d ago First seen · 154 lines · 88 tokens per session scan A 138554ced6b4
truth-maintenance is a skill published in the GitHub repository stellar-experimental/stellar-raven (6 stars, last pushed 3d ago), licensed Apache-2.0. It adds 88 tokens to every session and 2,006 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
cli-command
Design, implement, or review Composio CLI commands under ts/packages/cli using Effect, @effect/cli, services, output conventions, configuration and environment variables, and local vendor references. Use for CLI command UX, command wiring, service changes, or CLI source edits. Do not use for CLI E2E-only work; use…
bug-fixing
Fix defects in the Composio SDK repository with focused reproduction, root-cause analysis, regression tests, and narrow verification. Use when the user reports a bug, failing test, CI regression, runtime defect, or incorrect SDK behavior. Do not use for new feature design or broad refactors.
python-sdk
Implement or modify Python SDK behavior under python/composio, including tools, toolkits, sessions, auth configs, connected accounts, client integration, and shared Python models. Use for Python core runtime/API work; pair with python-testing and cross-sdk-parity when TypeScript must match.
python-testing
Select and run Python SDK verification with nox, Makefile targets, Ruff, mypy, pytest markers, sanity tests, type inference checks, and build checks. Use when adding Python tests, diagnosing Python CI, or validating Python SDK/provider changes. Do not use for TypeScript-only checks.
typescript-providers
Implement, modify, test, or document TypeScript provider packages under ts/packages/providers, including framework adapters for OpenAI, Anthropic, Google, LangChain, Mastra, Vercel, LlamaIndex, Cloudflare, and Claude Agent SDK. Use for provider-specific TS work; do not use for core-only changes.
typescript-sdk
Implement or modify TypeScript SDK behavior in @composio/core or shared TypeScript packages, including tools, toolkits, sessions, auth configs, connected accounts, modifiers, and generated SDK surfaces. Use for TS runtime/API work; pair with typescript-testing for verification and cross-sdk-parity when Python must…