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 skills add SteelMorgan/1c-agent-based-dev-framework --skill review-swarmgit clone --depth 1 https://github.com/SteelMorgan/1c-agent-based-dev-frameworkWrote 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/steelmorgan/1c-agent-based-dev-framework/review-swarm)<a href="https://agentmods.dev/skills/steelmorgan/1c-agent-based-dev-framework/review-swarm"><img src="https://agentmods.dev/badge/skills/steelmorgan/1c-agent-based-dev-framework/review-swarm/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/steelmorgan/1c-agent-based-dev-framework/review-swarm"><img src="https://agentmods.dev/badge/skills/steelmorgan/1c-agent-based-dev-framework/review-swarm.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00091 | $0.09318 |
| Opus 5.5 | $0.00036 | $0.03727 |
| Sonnet 5.5 | $0.00018 | $0.01864 |
| Haiku 4.5 | $0.00009 | $0.00932 |
Grade A, and why
review-swarm 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 17d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
42 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.
- examples/criticality-map.gbig-platform.md 7.6 KB
- references/criticality-map.md 7.6 KB
- references/design-decisions-e2e02.md 4.4 KB
- references/final-orchestrator-completion-review-prompt.md 5.0 KB
- references/finding-schema.md 5.3 KB
- references/report-template.md 1.4 KB
- references/review-prompt.md 3.7 KB
- references/review-report-template.md 4.2 KB
- references/track-record-swarm.md 11 KB
- references/verdict-schemas.md 11 KB
- scripts/swarm_core.py 74 KB runs code
- scripts/swarm.py 232 KB runs code
- tests/contract/conftest.py 2.4 KB runs code
- tests/contract/test_mixed_native_fork_roster.py 24 KB runs code
- tests/contract/test_native_fork_turn_lineage.py 13 KB runs code
- tests/integration/conftest.py 7.7 KB runs code
- tests/integration/swarm_case_helpers.py 2.2 KB runs code
- tests/integration/test_criticality_map.py 7.6 KB runs code
- tests/integration/test_dedup_replay_cli.py 10 KB runs code
- tests/integration/test_diff_delivery_guard.py 2.4 KB runs code
- tests/integration/test_e2e02_fixes_cli.py 27 KB runs code
- tests/integration/test_governance_links.py 6.2 KB runs code
- tests/integration/test_light_tier_gate.py 26 KB runs code
- tests/integration/test_rereview.py 16 KB runs code
- tests/integration/test_swarm_cli.py 24 KB runs code
- tests/pytest.ini 245 B
- tests/unit/conftest.py 417 B runs code
- tests/unit/test_budget.py 9.5 KB runs code
- tests/unit/test_dedup_replay.py 8.6 KB runs code
- tests/unit/test_dedup.py 17 KB runs code
- tests/unit/test_e2e02_fixes.py 16 KB runs code
- tests/unit/test_findings.py 11 KB runs code
- tests/unit/test_light_gate.py 14 KB runs code
- tests/unit/test_native_fork_lineage_faults.py 7.7 KB runs code
- tests/unit/test_native_fork_operator_cli.py 4.9 KB runs code
- tests/unit/test_native_phase_concurrency.py 7.4 KB runs code
- tests/unit/test_prompt_frames.py 3.1 KB runs code
- tests/unit/test_rereview_core.py 10 KB runs code
- tests/unit/test_rotation.py 9.6 KB runs code
- tests/unit/test_swarm_track_record.py 35 KB runs code
- tests/unit/test_triage.py 8.8 KB runs code
- tests/unit/test_validation_rounds.py 22 KB runs code
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.
- 17d ago Changed · +60 lines · +10 tokens per session 85b081e3c6dd
- 20d ago First seen · 461 lines · 81 tokens per session scan A 5a79ee100f67
review-swarm is a skill published in the GitHub repository SteelMorgan/1c-agent-based-dev-framework (119 stars, last pushed 18d ago), with no licence file. It adds 91 tokens to every session and 9,318 once invoked, about $0.0004 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 2026-09-28.
Other skills, from other repositories
1c-naparnik
A connection to 1C:Naparnik, a service for analyzing BSL code and searching 1C documentation and standards. BSL is the programming language used by the 1C:Enterprise platform.
bsp
A guide for developing and reviewing business software in 1C with its Standard Subsystems Library, a collection of shared building blocks for common tasks.
1c-code-review
A code-review procedure for BSL, the programming language used by the 1C business software platform. It checks changed code against a defect catalogue and labels each finding with an identifier, severity, and location.
bsl-change-review
A review skill for proposed changes to BSL code, forms, and metadata in 1C systems. It produces either a visual code difference or a copyable guide for making the changes by hand.
unica-development
A development workflow for researching, changing, and reviewing Unica's code, rules, and repository documentation.
code-review
A code-review aid for BSL code and 1C changes. Code review is the process of checking proposed code for defects and risks before it is accepted.