ShadowFrog is a suite of coding-agent skills that maintains a file-backed knowledge base of tacit information about a codebase, such as fragile dependencies, untested invariants, and hard-to-notice edge cases. It helps coding agents preserve lessons from code reading, experiments, and conversations across future work. The catalogue contains skills that create, update, explore, organize, and view this shadow knowledge base.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/microsoft/ShadowFrognpx agentmods add skills/microsoft/shadowfrog/shadow-frogWrote 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/microsoft/shadowfrog/shadow-frog)<a href="https://agentmods.dev/skills/microsoft/shadowfrog/shadow-frog"><img src="https://agentmods.dev/badge/skills/microsoft/shadowfrog/shadow-frog/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/microsoft/shadowfrog/shadow-frog"><img src="https://agentmods.dev/badge/skills/microsoft/shadowfrog/shadow-frog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 289 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00132 | $0.04559 |
| Opus 5.5 | $0.00053 | $0.01824 |
| Sonnet 5.5 | $0.00026 | $0.00912 |
| Haiku 4.5 | $0.00013 | $0.00456 |
Grade A, and why
shadow-frog 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 29d 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 — 469 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ShadowFrog
.shadow/ mirrors the source tree. Each source file has a .md shadow organized
by symbol. Each symbol section contains discoveries — behavioral insights anchored
to that code location.
Required Actions
Every time you work on code in a repo with .shadow/:
- Read
_prefs.mdfirst — it contains project-wide conventions, user preferences, and things to avoid. - Read relevant
_cross/discoveries — list_cross/and read entries whose titles relate to the current area, including cross-file contracts and interactions. - Check
_dreams/_index.mdand read relevant experiment reports, especially when investigating bugs or unfamiliar code. They may contain findings not yet distilled into per-file shadows. - Before editing a file, read its shadow (
.shadow/<path>.md) and relevant_cross/entries, then apply the discoveries._index.mdcounts may be stale; inspect the actual shadows and_cross/. - When the user explains something about code (gotcha, design intent,
warning, history): write a
source: userdiscovery to the shadow immediately. Resolve itsfile::symbolanchor from_index.md, shadows, and session context; do not ask where to put it. - When the user states a preference or convention (not tied to any
specific file): write it to
_prefs.mdimmediately. - After code changes: run
/shadow-frog-update
Record Revisited Knowledge
Continue navigating directly to shadow files and symbol headings. Each
discovery or preference has one visible citation_score: a nonnegative integer,
initially 0. Missing scores also mean 0. It is approximate, agent-reported
revisit frequency, not confidence or proof of usefulness.
When updating an existing shadow, preserve all knowledge and existing scores:
missing citation_score fields mean 0 and are added on the first recorded
citation, so no reinitialization is required.
After deliberately consulting an entry, record one citation for it per task. Do not count every entry merely because its file was opened, repeat the count on rereads, or count automatic previews that you did not use. Batch updates when practical; the agent/coordinator tracks which entries it already counted.
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.
- 29d ago Changed · +53 lines · +3 tokens per session 64a6ff551458
- 1mo ago Changed · -12 lines c4509f634d60
- 1mo ago Changed · +54 lines · +12 tokens per session 8bece998e35e
- 1mo ago First seen · 374 lines · 117 tokens per session scan A d50f78b029f9
shadow-frog is a skill published in the GitHub repository microsoft/ShadowFrog (30 stars, last pushed 6d ago), licensed MIT. It adds 132 tokens to every session and 4,559 once invoked, about $0.0005 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
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, timelines, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…