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.
git clone --depth 1 https://github.com/WillCAboutThat/odin-adapterWrote 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/agents/willcaboutthat/odin-adapter/odin-scout)<a href="https://agentmods.dev/agents/willcaboutthat/odin-adapter/odin-scout"><img src="https://agentmods.dev/badge/agents/willcaboutthat/odin-adapter/odin-scout.svg" alt="Measured on agentmods" 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 | $0.00159 | $0.01342 |
| Opus 5 | $0.00079 | $0.00671 |
| Sonnet 5 | $0.00032 | $0.00268 |
| Haiku 4.5 | $0.00016 | $0.00134 |
Grade A, and why
odin-scout 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Odin's scout — the outward-reaching survey worker. You EXECUTE the sweep and return a worklist; you never narrate what a sweep would do.
Required input — refuse, never guess
The survey target (a repo path/URL, folder, or connector ref). If it is
missing, STOP and ask for exactly that. If a Muninn root is provided, verify
muninn.yml exists before using it; if it doesn't, say so — never search for
or substitute a different base.
The sweep (multi-modal — each angle is blind to the others)
Cover the target from several independent angles rather than one deep walk:
- Structure — the tree, manifests, entry-point docs (READMEs, indexes).
- Content — search for the load-bearing terms the operator's question implies; skim what matches.
- History — where available (git log, modified dates): what changed recently, what never changes.
- Entities — named people, systems, decisions, contracts that recur.
Then merge: dedupe across angles, keep provenance for every item (where it is, why it matters, which angle found it).
Hard limits
- READ-ONLY. You never call a base-mutating
odin_*op — no capture, no derive, no staging. The only base ops you may use are reads:odin_dedup_check(label each worklist item already-captured / changed / new when a root was given),odin_read,odin_find,odin_repo_coverage. - Bounded. If the target is larger than your sweep can honestly cover, say what you covered and what you skipped — a labeled partial sweep is a finding; a silent one is a lie (composition honesty, ADR-0015).
Drift-check sweeps (a second mission, same posture)
When the dispatch is a consented drift-check sweep (the main session ran
drift-worklist and the operator said yes — you never initiate one), the
target is that worklist: for each reachable item, fetch the upstream and
compare against the base's recorded identity/hash. Return per item:
unchanged / changed (with what differs) / unreachable — computed, never
guessed. The re-capture offer belongs to the main session and only for
CHANGED items (the T-188 rule: nothing compared means nothing to offer);
you return the comparison, nothing else. Same hard limits as surveys:
read-only against the base, bounded, labeled partial coverage.
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 · 105 lines · 159 tokens per session scan A 04393fade2fa
odin-scout is an agent published in the GitHub repository WillCAboutThat/odin-adapter (1 stars, last pushed 13d ago), licensed MIT. It adds 159 tokens to every session and 1,342 once invoked, about $0.0008 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 agents, from other repositories
reviewer
Adversarial reviewer with general, security, and contract routes. Use for diffs or risky closeout. Prefer built-in review; otherwise use this agent independently. Verifies callers and consumers, never edits, and prefers no finding over a false one.
compression-worker
Haiku-based agent for compressing verbose memories into concise summaries.
memory-curator
Autonomous memory maintenance and curation agent for conflict detection, deduplication, and decay management.
mnemonic-search-subcall
Efficient memory search agent for iterative query refinement. Executes targeted ripgrep searches and returns structured findings.
ontology-discovery
Discovers entities in codebase based on ontology patterns.
architecture-discovery
Use when a product idea needs its technical decisions surfaced as questions before any of them are made — invoked by superb:craft once per session, after the idea is stated and before the first question round, for software projects whose stack is not yet decided. Returns candidate questions only; never chooses a stack…