argus
Skill0 starsChanged 2 months agoMITView on GitHub
Preserve durable context from conversations and completed work by routing commitments, evidence, decisions, preferences, and project state to their canonical Git-backed records. Use when the user asks to archive, remember, checkpoint, capture context, update an Archivum-style workspace, or close the loop; also use at natural milestones when workspace instructions require durable-state capture.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- realsee-developer/skillstheir own version, first seen Oct 29, 2026
- ardakaano/argustheir own version, first seen Oct 15, 2026
- shuvonsec/claude-bug-bountytheir own version, first seen Oct 8, 2026
- awarexone/Agentic-Bug-Huntertheir own version, first seen Jun 9, 2026
- Awarexone/Agentic-Bug-Huntertheir own version, first seen Jun 9, 2026
- korisame/argustheir own version, first seen May 6, 2026
Used with
Projects with it also use agentic-app-audit, client-reverse and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
shuvonsecSkillagentic-app-audit
Black-box security audit of a DEPLOYED AI agent (not the MCP server behind it) — tool-call hijacking, cross-session memory poisoning, confused-deputy via connected tools, agent-to-agent IDOR, excessive agency / unconfirmed destructive actions, and privilege compromise where the agent holds broader perms than the user. Use when the target is a live assistant/agent product with tool access (bookings, email, payments, file/RAG, browsing) rather than a raw LLM chat box or an MCP server you can read.
Also in 3 projects that use this
shuvonsecSkillclient-reverse
Client-side request-signing and anti-bot token reversal for bug bounty — when a request carries a sign/sig/hmac/token/nonce/timestamp/X-Sensor header that Burp Repeater cannot replay, recover the signer just enough to reproduce the request outside the client. Packet-first staging (capture real request → prove replay works → only reverse if replay fails) across the locate→recover→runtime→validation→replay spine. Covers tracing backward from the signature field (writer→builder→entry→source), isolating user-mutable sign inputs (timestamp/nonce/deviceId/body) vs constants (secret key), hooking fetch/XHR in DevTools, JS deobfuscation basics (webpack/wasm/JSVMP), and the bounty payoff: reach the protected API to then hunt IDOR/auth/business-logic. Use when Burp/mitmproxy replay of a signed or anti-bot-gated request fails and you suspect a client-computed field is blocking you.
Also in 3 projects that use this
Mikacr1138Skillweb2-vuln-classes
Complete reference for 18 web2 bug classes with root causes, detection patterns, bypass tables, exploit techniques, and real paid examples. Covers IDOR, auth bypass, XSS, SSRF (11 IP bypass techniques), SQLi, business logic, race conditions, OAuth/OIDC, file upload (10 bypass techniques), GraphQL, LLM/AI (ASI01-ASI10 agentic framework), API misconfig, ATO taxonomy, SSTI, subdomain takeover, cloud/infra misconfigs, HTTP smuggling, cache poisoning. Use when hunting a specific vuln class or studying what makes bugs pay.
Also in 3 projects that use this
hhjkjkjkSkillmeme-coin-audit
Meme coin and token security audit — rug pull detection (honeypot, hidden mint, fee manipulation, LP lock bypass), Solana SPL token analysis (freeze authority, mint authority, metadata mutability), Token-2022 extension risks (transfer hooks, permanent delegate), DEX liquidity pool attacks (sandwich amplification, LP drain, bonding curve exploits), pump.fun/Raydium/Jupiter integration risks, token_scanner.py automation, and real exploit examples from 2024-2025. Use for any token audit, rug pull assessment, meme coin security review, or pre-investment due diligence.
Also in 3 projects that use this
hhjkjkjkSkillbb-methodology
Use at the START of any bug bounty hunting session, when switching targets, or when feeling lost about what to do next. Master orchestrator that combines the 5-phase non-linear hunting workflow with the critical thinking framework (developer psychology, anomaly detection, What-If experiments). Routes to all other skills based on current hunting phase. Also use when asking "what should I do next" or "where am I in the process.
Also in 3 projects that use this
Mikacr1138Skillsecurity-arsenal
Security payloads, bypass tables, wordlists, gf pattern names, always-rejected bug list, and conditionally-valid-with-chain table. Use when you need specific payloads for XSS/SSRF/SQLi/XXE/IDOR/path-traversal, bypass techniques, or to check if a finding is submittable. Also use when asked about what NOT to submit.
Also in 3 projects that use this
- +6 more from shuvonsec
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- shuvonsec/claude-bug-bounty★ 5.5ksame name
- awarexone/Agentic-Bug-Hunter★ 5.5ksame name
- Awarexone/Agentic-Bug-Hunter★ 5.5ksame name
- realsee-developer/skills★ 11same name
- ardakaano/argus★ 2same name
- korisame/argus★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 9 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
9
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Keep a hundred eyes on the live context, but preserve only the delta that should outlive it.
- Distinctive: line 33
Verify changed files, links, schema or ledger checks, and relevant tests.
- Distinctive: line 44
Existing specialist Archivum: use when the project already has a canonical domain store.
- Distinctive: line 47
Read routing.md whenever a delta spans domains or has more than one plausible owner.
- Very specific: line 51
Treat a version-2 workspace's config.yaml as the authoritative path map.
- Distinctive: line 57
Run once after a meaningful milestone or before ending work that changed durable state.
- Distinctive: line 59
Do not recursively archive the mechanical fact that Argus updated an archive.
- Distinctive: line 60
If nothing durable changed, make no write and say nothing about capture.
- Distinctive: line 61
Treat a checkpoint as preservation authority, not permission to broaden scope or perform unrelated external actions.
- Distinctive: line 63
Use checkpoint-prompt.md to make Argus available automatically in repository-aware agents.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Argus
Keep a hundred eyes on the live context, but preserve only the delta that should outlive it. Do not archive the conversation itself.
Run one checkpoint
- Identify durable changes only:
- explicit decisions, corrections, and stable preferences;
- promises, deadlines, waiting-on states, and changed priorities;
- project state, evidence, results, blockers, and next actions;
- reusable methods, sources, and outputs.
- Exclude unselected brainstorming, conversational filler, duplicated summaries, unsupported claims, and secrets outside their authorised store.
Discover the home registry and candidate archives:
python3 scripts/discover_archivums.py --jsonResolve
scripts/relative to this installed skill. Prefer an explicit--registry, thenARCHIVUM_REGISTRY, then$ARCHIVUM_HOME/00_meta/archivum_registry.toml. If no registry resolves the choice and several archives remain plausible, ask rather than guess.- Route each delta using routing.md. One checkpoint may update several surfaces, but each fact has one canonical owner.
- For commitment-shaped state, use the workspace's configured commitment system rather than inventing a parallel ledger. Read its contract before mutation.
- For resource-shaped state or substantial autonomous work, use the configured budget authority rather than creating a second resource ledger. Gate expensive work and record actual usage where that system requires it.
- In each selected Archivum, read its agent contract and
config.yaml, then load only the bounded core context and record needed for the delta. Inspect its worktree and search before creating. - Apply the bidirectional home-anchor contract in backlink-contract.md. Every private satellite record must remain reachable from the home Archivum and link back to its home anchor.
- Verify changed files, links, schema or ledger checks, and relevant tests. Commit only where the archive contract or user requires it. Never publish, send, submit, or disclose merely because capture is complete.
- Report the durable records changed, surfaces intentionally untouched, and one next action if work remains.
Route by ownership, not keywords
- Commitment system: promises, deadlines, waiting on people, and current workstream custody.
- Budget authority: token and GPU budgets, account windows, autonomous-run gates, session histories, and artefact custody.
- Home Archivum: cross-domain projects, identity, relationships, personal decisions, stable preferences, and the cross-archive index.
- Research Archivum: hypotheses, literature, experiments, results, methods, and scientific strategy.
- Admin Archivum: company operations, governance, finance, legal, people operations, and internal administration.
- Career archive: role research, applications, evidence packets, and pipeline state.
- Existing specialist Archivum: use when the project already has a canonical domain store.
- New Archivum: propose only for a distinct audience, permission boundary, owner, or lifecycle. Never create one silently.
Read routing.md whenever a delta spans domains or has more than one plausible owner.
Respect each Archivum's configured layout
Treat a version-2 workspace's config.yaml as the authoritative path map. Resolve workspace.profile_file, workspace.state_file, workspace.schema_file, directories.*, and canonical_files.* from that file before reading or writing. Never assume numbered directory names such as 01_projects; the research Archivum, for example, maps projects to 01_active_research.
Read the selected archive's AGENTS.md first when present, then its configured profile, state, and schema only as needed. Prefer the archive-local archivum CLI for deterministic creation, status, and doctor checks when available. For a legacy workspace without version-2 configuration, inspect its existing structure and preserve it; do not migrate it unless the user requested migration.
Keep the watcher quiet
- Run once after a meaningful milestone or before ending work that changed durable state.
- Batch related deltas; never checkpoint after every edit or tool call.
- Do not recursively archive the mechanical fact that Argus updated an archive.
- If nothing durable changed, make no write and say nothing about capture.
- Treat a checkpoint as preservation authority, not permission to broaden scope or perform unrelated external actions.
Use checkpoint-prompt.md to make Argus available automatically in repository-aware agents.
Validate the archive graph
python3 scripts/discover_archivums.py --registry /path/to/00_meta/archivum_registry.toml --json
python3 scripts/check_backlinks.py --registry /path/to/00_meta/archivum_registry.tomlBoth scripts are read-only. Discovery also reports each Archivum's configuration version and available agent contracts. Backlink validation rejects logical paths that escape their registered archive root.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

