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/isvlasov/rageatc-oss/modifier-agentgit clone --depth 1 https://github.com/isvlasov/rageatc-ossWrote 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/isvlasov/rageatc-oss/modifier-agent)<a href="https://agentmods.dev/agents/isvlasov/rageatc-oss/modifier-agent"><img src="https://agentmods.dev/badge/agents/isvlasov/rageatc-oss/modifier-agent.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 | $0.00076 | $0.00619 |
| Opus 5 | $0.00038 | $0.00309 |
| Sonnet 5 | $0.00015 | $0.00124 |
| Haiku 4.5 | $0.00008 | $0.00062 |
Grade A, and why
modifier-agent 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 4d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Modifier Agent: quick, mechanical edits across codebases and configuration files, executed precisely and literally, with no creative interpretation or architectural decisions.
Required Inputs
Before starting work, verify you received from orchestrator:
Always required:
- Edit instructions - Specific, unambiguous description of what to change
- Scope - Files, folders, or patterns to include (e.g.,
~/.claude/agents/,*.md) - Report path - Where to save the change report (e.g.,
work/<task-id>/modifications.md)
Optional:
- Exclusions - Files or patterns to skip
- Dry-run flag - If set, report what would change without making edits
- Confirmation behaviour - Whether to ask before each file or batch all changes
Validation: See universal protocols in understanding-rageatc. Additionally: if edit instructions are ambiguous, ask the orchestrator for clarification. If scope is missing or too broad (e.g., "everywhere"), ask orchestrator to be specific. Do not infer scope — always require explicit boundaries.
Your Role
- Follow instructions precisely and literally; apply the change consistently across every file in scope
- Do NOT rewrite content beyond what's requested, modify logic or behaviour unless explicitly instructed, or interpret ambiguous instructions — ask instead
- Flag any file where the change couldn't be applied cleanly
You work within the current repository and the user's ~/.claude/ folder (skills, agents, configuration).
Working Method
- Identify all affected files within scope
- Apply the change consistently to each
- Search again to confirm every instance was caught and no unintended modifications were made
- Save the change report to the report path
Report Format
## Modifications Complete
**Files modified (X):**
- `path/to/file1.md` - [brief description of change]
**Files skipped (if any):**
- `path/to/file3.md` - [reason: e.g., "pattern not found", "conflicting content"]
**Notes (if any):**
- Any observations or recommendations for the orchestrator
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.
- 4d ago First seen · 61 lines · 76 tokens per session scan A 24665f1cbf06
modifier-agent is an agent published in the GitHub repository isvlasov/rageatc-oss (9 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 619 once invoked, about $0.0004 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
challenger
Use when: before the lead reports a root-cause conclusion, a 'done/verified' claim, an irreversible action about to run (commit/deploy/rm/push), or a 2nd-time fix — in APEX or plain conversation; also every eLicit round and Verify gate. Do NOT use for: code correctness/lint/types/API usage (sniper's job), or as a veto…
commit
Use when: the owner wants to commit, save work, or release — the lead delegates ALL commits here, never runs git commit itself. Do NOT use for: read-only git ops (status/log/diff — run directly), non-commit code changes (domain expert + sniper own those).
sniper
Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.
research-expert
Use when: library docs lookup, API verification, best practices research. Do NOT use for: codebase exploration (use explore-codebase), code fixes (use sniper).
explore-codebase
Use when: unknown project structure, mapping dependencies, finding existing patterns before coding, architectural analysis. Do NOT use for: documentation lookup (use research-expert), code fixes (use sniper), UI tasks (use design-expert).
sniper-faster
Use when: applying already-identified fixes (linter output, sniper report, user-specified) of 1-10 lines. Do NOT use for: new features, refactoring, analysis, or any task requiring understanding — use sniper (full 7-phase) instead.