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/tikalk/adlc-team-skillsnpx agentmods add skills/tikalk/adlc-team-skills/team-repairWrote 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/tikalk/adlc-team-skills/team-repair)<a href="https://agentmods.dev/skills/tikalk/adlc-team-skills/team-repair"><img src="https://agentmods.dev/badge/skills/tikalk/adlc-team-skills/team-repair/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/tikalk/adlc-team-skills/team-repair"><img src="https://agentmods.dev/badge/skills/tikalk/adlc-team-skills/team-repair.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Prompt Injection · line 155 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 295 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 1020 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00061 | $0.13391 |
| Opus 5.5 | $0.00024 | $0.05356 |
| Sonnet 5.5 | $0.00012 | $0.02678 |
| Haiku 4.5 | $0.00006 | $0.01339 |
Grade A, and why
team-repair 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 2d 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 — 1,315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
team-repair
Overview
Re-indexes OKF v0.2 artifacts (index.md, log.md), derives the flat CDR.md inject, rebuilds .skills.json and AGENTS.md in team-ai-directives to fix inconsistencies, detect orphaned files, and auto-repair issues. Migrates OKF v0.1 frontmatter to v0.2 on every run (always-on, no opt-out). Begins with a health-check phase (Phase 0) that verifies the directives framework is installed, configured, and aligned before performing any repairs.
Input: team-ai-directives repository
Output: 0. Health check report (7 checks: team AI directives configured, context modules exist, skills registry, OKF log tracking, constitution alignment, OKF v0.2 type field presence, project AGENTS.md directive)
- Repaired AGENTS.md (if missing or corrupted)
- Migrated all context module frontmatter from OKF v0.1 to v0.2 (always-on)
- Rebuilt per-directory
index.mdfiles (OKF §8 catalog) - Rebuilt per-directory
log.mdfiles (OKF §9 audit trail) - Derived
CDR.mdflat table fromindex.mdfiles (for team-boot system prompt injection) - Rebuilt .skills.json manifest from skills/
- Auto-added OKF v0.2 YAML frontmatter to orphan context modules
- Auto-generated .skills.json entries for orphan skills
- Conflict scan across rules (creates conflict CDRs if issues found)
- Freshness verification (updates
verifiedtimestamps, flags stale directives) - Draft validation report (if
--validate-drafts— read-only, no modifications) - Summary report of all repairs
You are acting as an Index Repair Specialist ensuring team-ai-directives indexes are consistent and complete. Your role involves:
- Verifying health checks before repair (Phase 0)
- Scanning context_modules/ and skills/ directories
- Detecting orphan files (missing frontmatter/manifest entries)
- Auto-repairing issues by generating missing metadata
- Rebuilding index files to reflect actual content
- Reporting all changes made
Repair Targets
| Target | Location | Purpose |
|---|---|---|
| AGENTS.md | {TEAM_AI_DIRECTIVES}/AGENTS.md |
Main instruction file for AI agents |
| index.md | {TEAM_AI_DIRECTIVES}/context_modules/**/index.md |
OKF §8 per-directory catalogs (progressive disclosure) |
| log.md | {TEAM_AI_DIRECTIVES}/context_modules/**/log.md |
OKF §9 per-directory audit trails |
| CDR.md | {TEAM_AI_DIRECTIVES}/CDR.md |
Derived flat table for team-boot system prompt injection (auto-generated from index.md files) |
| .skills.json | {TEAM_AI_DIRECTIVES}/.skills.json |
Skills manifest registry |
What ships with it
2 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.
- 2d ago Changed b9b30f194b1e
- 6d ago Changed 6bdcbf98d35e
- 24d ago Changed 9d499206608d
- 26d ago Changed 0ca08237cb03
- 27d ago Changed 25b6bc702834
- 1mo ago Changed · +180 lines · +18 tokens per session 3dd5979384f8
- 1mo ago Changed · +57 lines · -41 tokens per session f3e653c24831
- 1mo ago First seen · 1,078 lines · 84 tokens per session scan A 4347d769fd58
team-repair is a skill published in the GitHub repository tikalk/adlc-team-skills (143 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 13,391 once invoked, about $0.0002 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
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
decision-records
Use when a hard-to-reverse choice (database, framework, vendor, auth model) must be frozen as an immutable numbered ADR — the context that forced it, the options weighed, the decision, consequences both ways — or superseded without erasing history. NOT a meeting recap (that is meeting-notes), NOT standing project…
prompt-engineering
Use when one prompt must give the same right answer across reruns, models, and pasted-in hostile input: forcing a fixed schema, picking the few-shot set, ordering the prompt blocks, or the inline cases you run while tuning. NOT the agent loop, tools, or retrieval (that is building-agents), NOT a standing CI eval…
respect-the-oracle
Use when working against a test suite, spec, or graded harness you do not own - especially inside an automated loop scored on how many tests pass - and tempted to change the tests, weaken assertions, hardcode expected outputs, special-case inputs, or overfit the visible examples to turn things green.
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.