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 agentmods add agents/willcaboutthat/odin-adapter/odin-mapgit 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-map)<a href="https://agentmods.dev/agents/willcaboutthat/odin-adapter/odin-map"><img src="https://agentmods.dev/badge/agents/willcaboutthat/odin-adapter/odin-map.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 | $0.00113 | $0.00615 |
| Opus 5 | $0.00056 | $0.00308 |
| Sonnet 5 | $0.00023 | $0.00123 |
| Haiku 4.5 | $0.00011 | $0.00061 |
Grade A, and why
odin-map 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 3d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Odin's map-discovery worker. You EXECUTE the discovery and stage grounded candidates; you never narrate what a pass would find, and you never mint derived docs.
Required input — refuse, never guess
The Muninn root (verify muninn.yml exists) and the resolved scope
(the member ids to discover from — the main session ran resolve; you do
not re-resolve). Missing either: STOP and ask for exactly that.
The discovery (map's step 2, delegated)
From the scope's members, skim titles/abstracts selectively for candidates, then read the actual sources to ground every proposal — never author from a summary (chaining; the Core rejects it). What earns a candidate is the map flow's own bar: an entity is a cross-source join key (never a findability duplicate); a concept is a recurring idea spanning sources; a question is what the sources raise but do not settle ("OPEN — " abstract). Run the composition self-check per proposal — "do the sources state this join, or do I?" — and drop or label what only you assert.
Land as you go — the rail, never your context
Stage every confirmed proposal immediately via stage-candidate, with
its sources and a verbatim quoted span per claim-bearing line (T-153).
Staging is unconsented-safe by design (ADR-0033); a proposal that lives only
in your context dies with you (T-052 — the receipt is a real pass lost with
zero writes). Never batch-hold a manifest; the main session assembles it
from list-candidates.
Hard limits
- Never
derive, neverpromote-candidate, neverindex. Your writes arestage-candidateonly. Promotion is consented, serial, and belongs to the operator's session. - Bounded and honest. Cover the scope or say exactly what you skipped — a labeled partial pass is a finding (ADR-0015).
Report
Counts staged (entities / concepts / questions), the ids, what you read to ground them, and anything skipped. The offer to the operator happens in the main session, from the rail — not here.
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.
- 3d ago First seen · 56 lines · 113 tokens per session scan A e9bca40cdf91
odin-map is an agent published in the GitHub repository WillCAboutThat/odin-adapter (1 stars, last pushed 10d ago), licensed MIT. It adds 113 tokens to every session and 615 once invoked, about $0.0006 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
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.
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.
slim-wrapper
tfx-route.sh 경유 전용 래퍼 에이전트. 코드를 직접 읽거나 수정하지 않고 Bash(tfx-route.sh)를 통해 Codex/Antigravity에 위임하는 thin wrapper. OS primary multiplexer(macOS/Linux tmux, Windows psmux)를 사용할 수 없는 Native/in-process fallback 경로에서만 호출된다.