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 V-Songbird/slag/plugin install annealWrote 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/v-songbird/slag/overview)<a href="https://agentmods.dev/skills/v-songbird/slag/overview"><img src="https://agentmods.dev/badge/skills/v-songbird/slag/overview/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/v-songbird/slag/overview"><img src="https://agentmods.dev/badge/skills/v-songbird/slag/overview.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 | $0.00098 | $0.00773 |
| Opus 5.5 | $0.00039 | $0.00309 |
| Sonnet 5.5 | $0.00020 | $0.00155 |
| Haiku 4.5 | $0.00010 | $0.00077 |
Grade A, and why
overview 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 today.
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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Tell the owner, in one screen, what each part of anneal finds in this repository and which skill to run next. This skill reports and stops. It changes no file, runs no other skill and proposes no fix of its own.
Argument: $ARGUMENTS. A host that does not fill that in leaves it as written; read the argument from the request instead. With no-sessions, add --no-sessions to the command, so no past session is read.
Find the plugin's own files through ${CLAUDE_PLUGIN_ROOT} on Claude Code, or resolve ../../ from this file on other hosts. On Antigravity, give the command the project root the person named as its working directory, the Cwd of run_command; when they named none, ask for it first.
1. Run the script
node "<plugin root>/scripts/overview.js" --root "<repository root>"
The repository root is git rev-parse --show-toplevel, or the working directory outside Git. The script runs anneal's audit, documentation check, maintenance script and repeated-step search as they are and prints what each counted. It writes nothing and uses no model. It needs Node 22 or later; without Node, say so and stop. It can take half a minute on a project with many past sessions.
2. Show its lines
Show the script's output as it is: two lines per part, with what its script found and the skill to run next. Then add only this:
- the command for each
nexton this host:/anneal:<name>on Claude Code,$<name>on Codex,/<name>on Antigravity, with the argument the line gives; - for a part that says
not available, its reason in the script's words; - that the counts are heuristic findings, proposals and candidates, and that none is verified until its own skill reads the evidence.
| Part | Its skill | What that skill does |
|---|---|---|
| Navigation | repo-layout |
audits what makes an agent search, read or guess more than it needs to, and migrates with approval at each step |
| Documentation | repo-docs |
reconciles documentation and agent instructions with current behavior, trims what is stale, and writes or reviews one page or README |
| Past sessions | session-review all |
finds what many sessions repeat and proposes a script or a map-file line for it |
| This session | session-review |
finds where one session lost time and proposes map-file changes; session-review closeout checks whether a finished session is safe to delete |
What ships with it
3 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.
- today Changed 87a73e1ffc18
- 4d ago First seen · 45 lines · 98 tokens per session scan A 57faff27a071
overview is a skill published in the GitHub repository V-Songbird/slag (1 stars, last pushed today), licensed MIT. It adds 98 tokens to every session and 773 once invoked, about $0.0004 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 2026-11-10.
overview compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| overviewV-Songbird/slag | Skill | 1 | today | MIT | A | 98 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | 8d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |